Instansiasi salah satu kelas konfigurasi dari pustaka ini dari konfigurasi model pretrained.

Kelas konfigurasi yang akan diinstansiasi dipilih berdasarkan properti model_type dari objek config yang dimuat, atau, jika properti tersebut tidak ada, dengan menggunakan pencocokan pola pada pretrained_model_name_or_path:

• EvollaModel — EvollaConfig (model EvollaConfig)
• afmoe — AfmoeConfig (model AfmoeConfig)
• aimv2 — Aimv2Config (model Aimv2Config)
• aimv2_text_model — Aimv2TextConfig (model Aimv2TextConfig)
• aimv2_vision_model — Aimv2VisionConfig (model Aimv2VisionConfig)
• albert — AlbertConfig (model AlbertConfig)
• align — AlignConfig (model AlignConfig)
• align_text_model — AlignTextConfig (model AlignTextConfig)
• align_vision_model — AlignVisionConfig (model AlignVisionConfig)
• altclip — AltCLIPConfig (model AltCLIPConfig)
• altclip_text_model — AltCLIPTextConfig (model AltCLIPTextConfig)
• altclip_vision_model — AltCLIPVisionConfig (model AltCLIPVisionConfig)
• apertus — ApertusConfig (model ApertusConfig)
• arcee — ArceeConfig (model ArceeConfig)
• aria — AriaConfig (model AriaConfig)
• aria_text — AriaTextConfig (model AriaTextConfig)
• audio-spectrogram-transformer — ASTConfig (model ASTConfig)
• audioflamingo3 — AudioFlamingo3Config (model AudioFlamingo3Config)
• audioflamingo3_encoder — AudioFlamingo3EncoderConfig (model AudioFlamingo3EncoderConfig)
• autoformer — AutoformerConfig (model AutoformerConfig)
• axk1 — AXK1Config (model AXK1Config)
• axk2 — AXK2Config (model AXK2Config)
• aya_vision — AyaVisionConfig (model AyaVisionConfig)
• bailing_hybrid — BailingHybridConfig (model BailingHybridConfig)
• bamba — BambaConfig (model BambaConfig)
• bark — BarkConfig (model BarkConfig)
• bart — BartConfig (model BartConfig)
• beam — BeamConfig (model BeamConfig)
• beit — BeitConfig (model BeitConfig)
• bert — BertConfig (model BertConfig)
• bert-generation — BertGenerationConfig (model BertGenerationConfig)
• big_bird — BigBirdConfig (model BigBirdConfig)
• bigbird_pegasus — BigBirdPegasusConfig (model BigBirdPegasusConfig)
• biogpt — BioGptConfig (model BioGptConfig)
• bit — BitConfig (model BitConfig)
• bitnet — BitNetConfig (model BitNetConfig)
• blenderbot — BlenderbotConfig (model BlenderbotConfig)
• blenderbot-small — BlenderbotSmallConfig (model BlenderbotSmallConfig)
• blip — BlipConfig (model BlipConfig)
• blip-2 — Blip2Config (model Blip2Config)
• blip_2_qformer — Blip2QFormerConfig (model Blip2QFormerConfig)
• blip_2_vision_model — Blip2VisionConfig (model Blip2VisionConfig)
• blip_text_model — BlipTextConfig (model BlipTextConfig)
• blip_vision_model — BlipVisionConfig (model BlipVisionConfig)
• bloom — BloomConfig (model BloomConfig)
• blt — BltConfig (model BltConfig)
• blt_global_transformer — BltGlobalTransformerConfig (model BltGlobalTransformerConfig)
• blt_local_decoder — BltLocalDecoderConfig (model BltLocalDecoderConfig)
• blt_local_encoder — BltLocalEncoderConfig (model BltLocalEncoderConfig)
• blt_patcher — BltPatcherConfig (model BltPatcherConfig)
• bridgetower — BridgeTowerConfig (model BridgeTowerConfig)
• bridgetower_text_model — BridgeTowerTextConfig (model BridgeTowerTextConfig)
• bridgetower_vision_model — BridgeTowerVisionConfig (model BridgeTowerVisionConfig)
• bros — BrosConfig (model BrosConfig)
• camembert — CamembertConfig (model CamembertConfig)
• canary — CanaryConfig (model CanaryConfig)
• canary_decoder — CanaryDecoderConfig (model CanaryDecoderConfig)
• canine — CanineConfig (model CanineConfig)
• chameleon — ChameleonConfig (model ChameleonConfig)
• chameleon_vqgan — ChameleonVQVAEConfig (model ChameleonVQVAEConfig)
• chinese_clip — ChineseCLIPConfig (model ChineseCLIPConfig)
• chinese_clip_text_model — ChineseCLIPTextConfig (model ChineseCLIPTextConfig)
• chinese_clip_vision_model — ChineseCLIPVisionConfig (model ChineseCLIPVisionConfig)
• chmv2 — CHMv2Config (model CHMv2Config)
• clap — ClapConfig (model ClapConfig)
• clap_audio_model — ClapAudioConfig (model ClapAudioConfig)
• clap_text_model — ClapTextConfig (model ClapTextConfig)
• clip — CLIPConfig (model CLIPConfig)
• clip_text_model — CLIPTextConfig (model CLIPTextConfig)
• clip_vision_model — CLIPVisionConfig (model CLIPVisionConfig)
• clipseg — CLIPSegConfig (model CLIPSegConfig)
• clipseg_text_model — CLIPSegTextConfig (model CLIPSegTextConfig)
• clipseg_vision_model — CLIPSegVisionConfig (model CLIPSegVisionConfig)
• clvp — ClvpConfig (model ClvpConfig)
• clvp_decoder — ClvpDecoderConfig (model ClvpDecoderConfig)
• clvp_encoder — ClvpEncoderConfig (model ClvpEncoderConfig)
• codegen — CodeGenConfig (model CodeGenConfig)
• cohere — CohereConfig (model CohereConfig)
• cohere2 — Cohere2Config (model Cohere2Config)
• cohere2_moe — Cohere2MoeConfig (model Cohere2MoeConfig)
• cohere2_vision — Cohere2VisionConfig (model Cohere2VisionConfig)
• cohere_asr — CohereAsrConfig (model CohereAsrConfig)
• cohere_compass — CohereCompassConfig (model CohereCompassConfig)
• cohere_compass_text — CohereCompassTextConfig (model CohereCompassTextConfig)
• cohere_compass_vision — CohereCompassVisionConfig (model CohereCompassVisionConfig)
• colmodernvbert — ColModernVBertConfig (model ColModernVBertConfig)
• colpali — ColPaliConfig (model ColPaliConfig)
• colqwen2 — ColQwen2Config (model ColQwen2Config)
• conditional_detr — ConditionalDetrConfig (model ConditionalDetrConfig)
• convbert — ConvBertConfig (model ConvBertConfig)
• convnext — ConvNextConfig (model ConvNextConfig)
• convnextv2 — ConvNextV2Config (model ConvNextV2Config)
• cosmos3_edge — Cosmos3EdgeConfig (model Cosmos3EdgeConfig)
• cosmos3_edge_text — Cosmos3EdgeTextConfig (model Cosmos3EdgeTextConfig)
• cosmos3_edge_vision — Cosmos3EdgeVisionConfig (model Cosmos3EdgeVisionConfig)
• cosmos3_omni — Cosmos3OmniConfig (model Cosmos3OmniConfig)
• cpmant — CpmAntConfig (model CpmAntConfig)
• csm — CsmConfig (model CsmConfig)
• csm_depth_decoder_model — CsmDepthDecoderConfig (model CsmDepthDecoderConfig)
• ctrl — CTRLConfig (model CTRLConfig)
• cvt — CvtConfig (model CvtConfig)
• cwm — CwmConfig (model CwmConfig)
• d_fine — DFineConfig (model DFineConfig)
• dab-detr — DabDetrConfig (model DabDetrConfig)
• dac — DacConfig (model DacConfig)
• data2vec-audio — Data2VecAudioConfig (model Data2VecAudioConfig)
• data2vec-text — Data2VecTextConfig (model Data2VecTextConfig)
• data2vec-vision — Data2VecVisionConfig (model Data2VecVisionConfig)
• dbrx — DbrxConfig (model DbrxConfig)
• deberta — DebertaConfig (model DebertaConfig)
• deberta-v2 — DebertaV2Config (model DebertaV2Config)
• decision_transformer — DecisionTransformerConfig (model DecisionTransformerConfig)
• deepseek_ocr2 — DeepseekOcr2Config (model DeepseekOcr2Config)
• deepseek_ocr2_encoder — DeepseekOcr2VisionEncoderConfig (model DeepseekOcr2VisionEncoderConfig)
• deepseek_ocr2_sam_vision_model — DeepseekOcr2SamVisionConfig (model DeepseekOcr2SamVisionConfig)
• deepseek_ocr2_text — DeepseekOcr2TextConfig (model DeepseekOcr2TextConfig)
• deepseek_ocr2_vision — DeepseekOcr2VisionConfig (model DeepseekOcr2VisionConfig)
• deepseek_v2 — DeepseekV2Config (model DeepseekV2Config)
• deepseek_v3 — DeepseekV3Config (model DeepseekV3Config)
• deepseek_v32 — DeepseekV32Config (model DeepseekV32Config)
• deepseek_v4 — DeepseekV4Config (model DeepseekV4Config)
• deepseek_vl — DeepseekVLConfig (model DeepseekVLConfig)
• deepseek_vl_hybrid — DeepseekVLHybridConfig (model DeepseekVLHybridConfig)
• deformable_detr — DeformableDetrConfig (model DeformableDetrConfig)
• deimv2 — Deimv2Config (model Deimv2Config)
• deit — DeiTConfig (model DeiTConfig)
• depth_anything — DepthAnythingConfig (model DepthAnythingConfig)
• depth_pro — DepthProConfig (model DepthProConfig)
• detr — DetrConfig (model DetrConfig)
• dia — DiaConfig (model DiaConfig)
• dia_decoder — DiaDecoderConfig (model DiaDecoderConfig)
• dia_encoder — DiaEncoderConfig (model DiaEncoderConfig)
• diffllama — DiffLlamaConfig (model DiffLlamaConfig)
• diffusion_gemma — DiffusionGemmaConfig (model DiffusionGemmaConfig)
• diffusion_gemma_text — DiffusionGemmaTextConfig (model DiffusionGemmaTextConfig)
• dinat — DinatConfig (model DinatConfig)
• dinov2 — Dinov2Config (model Dinov2Config)
• dinov2_with_registers — Dinov2WithRegistersConfig (model Dinov2WithRegistersConfig)
• dinov3_convnext — DINOv3ConvNextConfig (model DINOv3ConvNextConfig)
• dinov3_vit — DINOv3ViTConfig (model DINOv3ViTConfig)
• distilbert — DistilBertConfig (model DistilBertConfig)
• doge — DogeConfig (model DogeConfig)
• donut-swin — DonutSwinConfig (model DonutSwinConfig)
• dots1 — Dots1Config (model Dots1Config)
• dpr — DPRConfig (model DPRConfig)
• dpt — DPTConfig (model DPTConfig)
• edgetam — EdgeTamConfig (model EdgeTamConfig)
• edgetam_mask_decoder — EdgeTamMaskDecoderConfig (model EdgeTamMaskDecoderConfig)
• edgetam_prompt_encoder — EdgeTamPromptEncoderConfig (model EdgeTamPromptEncoderConfig)
• edgetam_video — EdgeTamVideoConfig (model EdgeTamVideoConfig)
• edgetam_video_mask_decoder — EdgeTamVideoMaskDecoderConfig (model EdgeTamVideoMaskDecoderConfig)
• edgetam_video_prompt_encoder — EdgeTamVideoPromptEncoderConfig (model EdgeTamVideoPromptEncoderConfig)
• edgetam_vision_model — EdgeTamVisionConfig (model EdgeTamVisionConfig)
• efficientloftr — EfficientLoFTRConfig (model EfficientLoFTRConfig)
• efficientnet — EfficientNetConfig (model EfficientNetConfig)
• electra — ElectraConfig (model ElectraConfig)
• embedding_gemma2 — EmbeddingGemma2Config (model EmbeddingGemma2Config)
• embedding_gemma2_text — EmbeddingGemma2TextConfig (model EmbeddingGemma2TextConfig)
• emu3 — Emu3Config (model Emu3Config)
• emu3_text_model — Emu3TextConfig (model Emu3TextConfig)
• emu3_vqgan — Emu3VQVAEConfig (model Emu3VQVAEConfig)
• encodec — EncodecConfig (model EncodecConfig)
• encoder-decoder — EncoderDecoderConfig (model EncoderDecoderConfig)
• eomt — EomtConfig (model EomtConfig)
• eomt_dinov3 — EomtDinov3Config (model EomtDinov3Config)
• ernie — ErnieConfig (model ErnieConfig)
• ernie4_5 — Ernie4_5Config (model Ernie4_5Config)
• ernie4_5_moe — Ernie4_5_MoeConfig (model Ernie4_5_MoeConfig)
• ernie4_5_vl_moe — Ernie4_5_VLMoeConfig (model Ernie4_5_VLMoeConfig)
• ernie4_5_vl_moe_text — Ernie4_5_VLMoeTextConfig (model Ernie4_5_VLMoeTextConfig)
• ernie4_5_vl_moe_vision — Ernie4_5_VLMoeVisionConfig (model Ernie4_5_VLMoeVisionConfig)
• esm — EsmConfig (model EsmConfig)
• esmc — EsmcConfig (model EsmcConfig)
• esmfold2 — EsmFold2Config (model EsmFold2Config)
• eurobert — EuroBertConfig (model EuroBertConfig)
• evolla — EvollaConfig (model EvollaConfig)
• exaone4 — Exaone4Config (model Exaone4Config)
• exaone4_5 — Exaone4_5_Config (model Exaone4_5_Config)
• exaone4_5_vision — Exaone4_5_VisionConfig (model Exaone4_5_VisionConfig)
• exaone_moe — ExaoneMoeConfig (model ExaoneMoeConfig)
• falcon — FalconConfig (model FalconConfig)
• falcon_h1 — FalconH1Config (model FalconH1Config)
• falcon_mamba — FalconMambaConfig (model FalconMambaConfig)
• fast_vlm — FastVlmConfig (model FastVlmConfig)
• fastspeech2_conformer — FastSpeech2ConformerConfig (model FastSpeech2ConformerConfig)
• fastspeech2_conformer_hifigan — FastSpeech2ConformerHifiGanConfig (model FastSpeech2ConformerHifiGanConfig)
• fastspeech2_conformer_with_hifigan — FastSpeech2ConformerWithHifiGanConfig (model FastSpeech2ConformerWithHifiGanConfig)
• flaubert — FlaubertConfig (model FlaubertConfig)
• flava — FlavaConfig (model FlavaConfig)
• flava_image_codebook — FlavaImageCodebookConfig (model FlavaImageCodebookConfig)
• flava_image_model — FlavaImageConfig (model FlavaImageConfig)
• flava_multimodal_model — FlavaMultimodalConfig (model FlavaMultimodalConfig)
• flava_text_model — FlavaTextConfig (model FlavaTextConfig)
• flex_olmo — FlexOlmoConfig (model FlexOlmoConfig)
• flint — FlintConfig (model FlintConfig)
• florence2 — Florence2Config (model Florence2Config)
• florence_vision — Florence2VisionConfig (model Florence2VisionConfig)
• fnet — FNetConfig (model FNetConfig)
• focalnet — FocalNetConfig (model FocalNetConfig)
• fsmt — FSMTConfig (model FSMTConfig)
• fun_asr_nano — FunAsrNanoConfig (model FunAsrNanoConfig)
• fun_asr_nano_encoder — FunAsrNanoEncoderConfig (model FunAsrNanoEncoderConfig)
• funnel — FunnelConfig (model FunnelConfig)
• fuyu — FuyuConfig (model FuyuConfig)
• gemma — GemmaConfig (model GemmaConfig)
• gemma2 — Gemma2Config (model Gemma2Config)
• gemma3 — Gemma3Config (model Gemma3Config)
• gemma3_text — Gemma3TextConfig (model Gemma3TextConfig)
• gemma3n — Gemma3nConfig (model Gemma3nConfig)
• gemma3n_audio — Gemma3nAudioConfig (model Gemma3nAudioConfig)
• gemma3n_text — Gemma3nTextConfig (model Gemma3nTextConfig)
• gemma3n_vision — Gemma3nVisionConfig (model Gemma3nVisionConfig)
• gemma4 — Gemma4Config (model Gemma4Config)
• gemma4_assistant — Gemma4AssistantConfig (model Gemma4AssistantConfig)
• gemma4_audio — Gemma4AudioConfig (model Gemma4AudioConfig)
• gemma4_text — Gemma4TextConfig (model Gemma4TextConfig)
• gemma4_unified — Gemma4UnifiedConfig (model Gemma4UnifiedConfig)
• gemma4_unified_assistant — Gemma4UnifiedAssistantConfig (model Gemma4UnifiedAssistantConfig)
• gemma4_unified_audio — Gemma4UnifiedAudioConfig (model Gemma4UnifiedAudioConfig)
• gemma4_unified_text — Gemma4UnifiedTextConfig (model Gemma4UnifiedTextConfig)
• gemma4_unified_vision — Gemma4UnifiedVisionConfig (model Gemma4UnifiedVisionConfig)
• gemma4_vision — Gemma4VisionConfig (model Gemma4VisionConfig)
• git — GitConfig (model GitConfig)
• git_vision_model — GitVisionConfig (model GitVisionConfig)
• glm — GlmConfig (model GlmConfig)
• glm4 — Glm4Config (model Glm4Config)
• glm46v — Glm46VConfig (model Glm46VConfig)
• glm4_moe — Glm4MoeConfig (model Glm4MoeConfig)
• glm4_moe_lite — Glm4MoeLiteConfig (model Glm4MoeLiteConfig)
• glm4v — Glm4vConfig (model Glm4vConfig)
• glm4v_moe — Glm4vMoeConfig (model Glm4vMoeConfig)
• glm4v_moe_text — Glm4vMoeTextConfig (model Glm4vMoeTextConfig)
• glm4v_moe_vision — Glm4vMoeVisionConfig (model Glm4vMoeVisionConfig)
• glm4v_text — Glm4vTextConfig (model Glm4vTextConfig)
• glm4v_vision — Glm4vVisionConfig (model Glm4vVisionConfig)
• glm5_next — Glm5NextConfig (model Glm5NextConfig)
• glm5_next_text — Glm5NextTextConfig (model Glm5NextTextConfig)
• glm5_next_vision — Glm5NextVisionConfig (model Glm5NextVisionConfig)
• glm_image — GlmImageConfig (model GlmImageConfig)
• glm_image_text — GlmImageTextConfig (model GlmImageTextConfig)
• glm_image_vision — GlmImageVisionConfig (model GlmImageVisionConfig)
• glm_image_vqmodel — GlmImageVQVAEConfig (model GlmImageVQVAEConfig)
• glm_moe_dsa — GlmMoeDsaConfig (model GlmMoeDsaConfig)
• glm_ocr — GlmOcrConfig (model GlmOcrConfig)
• glm_ocr_text — GlmOcrTextConfig (model GlmOcrTextConfig)
• glm_ocr_vision — GlmOcrVisionConfig (model GlmOcrVisionConfig)
• glmasr — GlmAsrConfig (model GlmAsrConfig)
• glmasr_encoder — GlmAsrEncoderConfig (model GlmAsrEncoderConfig)
• glmga — GlmgaConfig (model GlmgaConfig)
• glpn — GLPNConfig (model GLPNConfig)
• got_ocr2 — GotOcr2Config (model GotOcr2Config)
• got_ocr2_vision — GotOcr2VisionConfig (model GotOcr2VisionConfig)
• gpt-sw3 — GPT2Config (model GPT2Config)
• gpt2 — GPT2Config (model GPT2Config)
• gpt_bigcode — GPTBigCodeConfig (model GPTBigCodeConfig)
• gpt_neo — GPTNeoConfig (model GPTNeoConfig)
• gpt_neox — GPTNeoXConfig (model GPTNeoXConfig)
• gpt_neox_japanese — GPTNeoXJapaneseConfig (model GPTNeoXJapaneseConfig)
• gpt_oss — GptOssConfig (model GptOssConfig)
• gptj — GPTJConfig (model GPTJConfig)
• gradium_phonon_tts — GradiumPhononTTSConfig (model GradiumPhononTTSConfig)
• granite — GraniteConfig (model GraniteConfig)
• granite4_vision — Granite4VisionConfig (model Granite4VisionConfig)
• granite4_vision_text — Granite4VisionTextConfig (model Granite4VisionTextConfig)
• granite_speech — GraniteSpeechConfig (model GraniteSpeechConfig)
• granite_speech5_ctc — GraniteSpeech5CTCConfig (model GraniteSpeech5CTCConfig)
• granite_speech5_encoder — GraniteSpeech5EncoderConfig (model GraniteSpeech5EncoderConfig)
• granite_speech_encoder — GraniteSpeechEncoderConfig (model GraniteSpeechEncoderConfig)
• granite_speech_plus — GraniteSpeechPlusConfig (model GraniteSpeechPlusConfig)
• granite_speech_plus_encoder — GraniteSpeechPlusEncoderConfig (model GraniteSpeechPlusEncoderConfig)
• granite_swa — GraniteSWAConfig (model GraniteSWAConfig)
• granitemoe — GraniteMoeConfig (model GraniteMoeConfig)
• granitemoe_swa — GraniteMoeSWAConfig (model GraniteMoeSWAConfig)
• granitemoehybrid — GraniteMoeHybridConfig (model GraniteMoeHybridConfig)
• granitemoeshared — GraniteMoeSharedConfig (model GraniteMoeSharedConfig)
• grounding-dino — GroundingDinoConfig (model GroundingDinoConfig)
• groupvit — GroupViTConfig (model GroupViTConfig)
• groupvit_text_model — GroupViTTextConfig (model GroupViTTextConfig)
• groupvit_vision_model — GroupViTVisionConfig (model GroupViTVisionConfig)
• gte — GteConfig (model GteConfig)
• helium — HeliumConfig (model HeliumConfig)
• hgnet_v2 — HGNetV2Config (model HGNetV2Config)
• hiera — HieraConfig (model HieraConfig)
• higgs_audio_v2 — HiggsAudioV2Config (model HiggsAudioV2Config)
• higgs_audio_v2_tokenizer — HiggsAudioV2TokenizerConfig (model HiggsAudioV2TokenizerConfig)
• hrm_text — HrmTextConfig (model HrmTextConfig)
• hubert — HubertConfig (model HubertConfig)
• hunyuan_v1_dense — HunYuanDenseV1Config (model HunYuanDenseV1Config)
• hunyuan_v1_moe — HunYuanMoEV1Config (model HunYuanMoEV1Config)
• hunyuan_vl — HunYuanVLConfig (model HunYuanVLConfig)
• hunyuan_vl_text — HunYuanVLTextConfig (model HunYuanVLTextConfig)
• hunyuan_vl_vision — HunYuanVLVisionConfig (model HunYuanVLVisionConfig)
• hy_v3 — HYV3Config (model HYV3Config)
• hy_v4 — HYV4Config (model HYV4Config)
• hyperclovax — HyperCLOVAXConfig (model HyperCLOVAXConfig)
• hyperclovax_vision_v2 — HyperCLOVAXVisionV2Config (model HyperCLOVAXVisionV2Config)
• ibert — IBertConfig (model IBertConfig)
• idefics — IdeficsConfig (model IdeficsConfig)
• idefics2 — Idefics2Config (model Idefics2Config)
• idefics2_perceiver — Idefics2PerceiverConfig (model Idefics2PerceiverConfig)
• idefics2_vision — Idefics2VisionConfig (model Idefics2VisionConfig)
• idefics3 — Idefics3Config (model Idefics3Config)
• idefics3_vision — Idefics3VisionConfig (model Idefics3VisionConfig)
• idefics_perciever — IdeficsPerceiverConfig (model IdeficsPerceiverConfig)
• idefics_vision — IdeficsVisionConfig (model IdeficsVisionConfig)
• ijepa — IJepaConfig (model IJepaConfig)
• imagegpt — ImageGPTConfig (model ImageGPTConfig)
• informer — InformerConfig (model InformerConfig)
• inkling_audio — InklingAudioConfig (model InklingAudioConfig)
• inkling_mm_model — InklingConfig (model InklingConfig)
• inkling_text — InklingTextConfig (model InklingTextConfig)
• inkling_vision — InklingVisionConfig (model InklingVisionConfig)
• instructblip — InstructBlipConfig (model InstructBlipConfig)
• instructblip_qformer — InstructBlipQFormerConfig (model InstructBlipQFormerConfig)
• instructblip_vision_model — InstructBlipVisionConfig (model InstructBlipVisionConfig)
• instructblipvideo — InstructBlipVideoConfig (model InstructBlipVideoConfig)
• instructblipvideo_qformer — InstructBlipVideoQFormerConfig (model InstructBlipVideoQFormerConfig)
• instructblipvideo_vision_model — InstructBlipVideoVisionConfig (model InstructBlipVideoVisionConfig)
• internvl — InternVLConfig (model InternVLConfig)
• internvl_vision — InternVLVisionConfig (model InternVLVisionConfig)
• jais2 — Jais2Config (model Jais2Config)
• jamba — JambaConfig (model JambaConfig)
• janus — JanusConfig (model JanusConfig)
• janus_vision_model — JanusVisionConfig (model JanusVisionConfig)
• janus_vqgan — JanusVQVAEConfig (model JanusVQVAEConfig)
• jetmoe — JetMoeConfig (model JetMoeConfig)
• jina_embeddings_v3 — JinaEmbeddingsV3Config (model JinaEmbeddingsV3Config)
• kimi_k25 — Kimi_K25Config (model Kimi_K25Config)
• kimi_k25_vision — Kimi_K25VisionConfig (model Kimi_K25VisionConfig)
• kimi_linear — KimiLinearConfig (model KimiLinearConfig)
• kolibri1 — Kolibri1Config (model Kolibri1Config)
• kosmos-2 — Kosmos2Config (model Kosmos2Config)
• kosmos-2.5 — Kosmos2_5Config (model Kosmos2_5Config)
• kosmos_2_5_text_model — Kosmos2_5TextConfig (model Kosmos2_5TextConfig)
• kosmos_2_5_vision_model — Kosmos2_5VisionConfig (model Kosmos2_5VisionConfig)
• kosmos_2_text_model — Kosmos2TextConfig (model Kosmos2TextConfig)
• kosmos_2_vision_model — Kosmos2VisionConfig (model Kosmos2VisionConfig)
• kyutai_speech_to_text — KyutaiSpeechToTextConfig (model KyutaiSpeechToTextConfig)
• laguna — LagunaConfig (model LagunaConfig)
• lasr_ctc — LasrCTCConfig (model LasrCTCConfig)
• lasr_encoder — LasrEncoderConfig (model LasrEncoderConfig)
• layoutlm — LayoutLMConfig (model LayoutLMConfig)
• layoutlmv2 — LayoutLMv2Config (model LayoutLMv2Config)
• layoutlmv3 — LayoutLMv3Config (model LayoutLMv3Config)
• layoutxlm — LayoutXLMConfig (model LayoutXLMConfig)
• led — LEDConfig (model LEDConfig)
• levit — LevitConfig (model LevitConfig)
• lfm2 — Lfm2Config (model Lfm2Config)
• lfm2_moe — Lfm2MoeConfig (model Lfm2MoeConfig)
• lfm2_vl — Lfm2VlConfig (model Lfm2VlConfig)
• lightglue — LightGlueConfig (model LightGlueConfig)
• lighton_ocr — LightOnOcrConfig (model LightOnOcrConfig)
• lilt — LiltConfig (model LiltConfig)
• llama — LlamaConfig (model LlamaConfig)
• llama4 — Llama4Config (model Llama4Config)
• llama4_text — Llama4TextConfig (model Llama4TextConfig)
• llama4_vision_model — Llama4VisionConfig (model Llama4VisionConfig)
• llava — LlavaConfig (model LlavaConfig)
• llava_next — LlavaNextConfig (model LlavaNextConfig)
• llava_next_video — LlavaNextVideoConfig (model LlavaNextVideoConfig)
• llava_onevision — LlavaOnevisionConfig (model LlavaOnevisionConfig)
• longcat_flash — LongcatFlashConfig (model LongcatFlashConfig)
• longformer — LongformerConfig (model LongformerConfig)
• longt5 — LongT5Config (model LongT5Config)
• luke — LukeConfig (model LukeConfig)
• lw_detr — LwDetrConfig (model LwDetrConfig)
• lw_detr_vit — LwDetrViTConfig (model LwDetrViTConfig)
• lxmert — LxmertConfig (model LxmertConfig)
• m2m_100 — M2M100Config (model M2M100Config)
• mamba — MambaConfig (model MambaConfig)
• mamba2 — Mamba2Config (model Mamba2Config)
• marian — MarianConfig (model MarianConfig)
• markuplm — MarkupLMConfig (model MarkupLMConfig)
• mask2former — Mask2FormerConfig (model Mask2FormerConfig)
• maskformer — MaskFormerConfig (model MaskFormerConfig)
• maskformer-swin — MaskFormerSwinConfig (model MaskFormerSwinConfig)
• mbart — MBartConfig (model MBartConfig)
• megatron-bert — MegatronBertConfig (model MegatronBertConfig)
• mellum — MellumConfig (model MellumConfig)
• metaclip_2 — MetaClip2Config (model MetaClip2Config)
• metaclip_2_text_model — MetaClip2TextConfig (model MetaClip2TextConfig)
• metaclip_2_vision_model — MetaClip2VisionConfig (model MetaClip2VisionConfig)
• mgp-str — MgpstrConfig (model MgpstrConfig)
• mimi — MimiConfig (model MimiConfig)
• mimi_decoder — MimiDecoderConfig (model MimiDecoderConfig)
• mimi_encoder — MimiEncoderConfig (model MimiEncoderConfig)
• mimo_v2_flash — MiMoV2FlashConfig (model MiMoV2FlashConfig)
• minicpm3 — MiniCPM3Config (model MiniCPM3Config)
• minicpm_ocr — MiniCPMOcrConfig (model MiniCPMOcrConfig)
• minicpm_ocr_vision — MiniCPMOcrVisionConfig (model MiniCPMOcrVisionConfig)
• minicpmv4_6 — MiniCPMV4_6Config (model MiniCPMV4_6Config)
• minicpmv4_6_vision — MiniCPMV4_6VisionConfig (model MiniCPMV4_6VisionConfig)
• minicpmv4_7 — MiniCPMV4_7Config (model MiniCPMV4_7Config)
• minicpmv4_7_vision — MiniCPMV4_7VisionConfig (model MiniCPMV4_7VisionConfig)
• minimax — MiniMaxConfig (model MiniMaxConfig)
• minimax_m2 — MiniMaxM2Config (model MiniMaxM2Config)
• minimax_m3_vl — MiniMaxM3VLConfig (model MiniMaxM3VLConfig)
• minimax_m3_vl_text — MiniMaxM3VLTextConfig (model MiniMaxM3VLTextConfig)
• minimax_m3_vl_vision — MiniMaxM3VLVisionConfig (model MiniMaxM3VLVisionConfig)
• ministral — MinistralConfig (model MinistralConfig)
• ministral3 — Ministral3Config (model Ministral3Config)
• mistral — MistralConfig (model MistralConfig)
• mistral3 — Mistral3Config (model Mistral3Config)
• mistral4 — Mistral4Config (model Mistral4Config)
• mistral_large4 — MistralLarge4Config (model MistralLarge4Config)
• mistral_large4_text — MistralLarge4TextConfig (model MistralLarge4TextConfig)
• mixtral — MixtralConfig (model MixtralConfig)
• mlcd — MLCDVisionConfig (model MLCDVisionConfig)
• mlcd_vision_model — MLCDVisionConfig (model MLCDVisionConfig)
• mllama — MllamaConfig (model MllamaConfig)
• mllama_text_model — MllamaTextConfig (model MllamaTextConfig)
• mllama_vision_model — MllamaVisionConfig (model MllamaVisionConfig)
• mm-grounding-dino — MMGroundingDinoConfig (model MMGroundingDinoConfig)
• mobilebert — MobileBertConfig (model MobileBertConfig)
• mobilenet_v1 — MobileNetV1Config (model MobileNetV1Config)
• mobilenet_v2 — MobileNetV2Config (model MobileNetV2Config)
• mobilevit — MobileViTConfig (model MobileViTConfig)
• mobilevitv2 — MobileViTV2Config (model MobileViTV2Config)
• modernbert — ModernBertConfig (model ModernBertConfig)
• modernbert-decoder — ModernBertDecoderConfig (model ModernBertDecoderConfig)
• modernvbert — ModernVBertConfig (model ModernVBertConfig)
• molmo2 — Molmo2Config (model Molmo2Config)
• molmo2_adapter — Molmo2AdapterConfig (model Molmo2AdapterConfig)
• molmo2_text — Molmo2TextConfig (model Molmo2TextConfig)
• molmo2_vision — Molmo2VisionConfig (model Molmo2VisionConfig)
• moonshine — MoonshineConfig (model MoonshineConfig)
• moonshine_streaming — MoonshineStreamingConfig (model MoonshineStreamingConfig)
• moonshine_streaming_encoder — MoonshineStreamingEncoderConfig (model MoonshineStreamingEncoderConfig)
• moshi — MoshiConfig (model MoshiConfig)
• moshi_depth — MoshiDepthConfig (model MoshiDepthConfig)
• moss_transcribe_diarize — MossTranscribeDiarizeConfig (model MossTranscribeDiarizeConfig)
• moss_transcribe_diarize_audio — MossTranscribeDiarizeAudioConfig (model MossTranscribeDiarizeAudioConfig)
• mpnet — MPNetConfig (model MPNetConfig)
• mpt — MptConfig (model MptConfig)
• mra — MraConfig (model MraConfig)
• mt5 — MT5Config (model MT5Config)
• muse_glimmer — MuseGlimmerConfig (model MuseGlimmerConfig)
• muse_glimmer_assistant — MuseGlimmerAssistantConfig (model MuseGlimmerAssistantConfig)
• muse_glimmer_text — MuseGlimmerTextConfig (model MuseGlimmerTextConfig)
• muse_glimmer_vision — MuseGlimmerVisionConfig (model MuseGlimmerVisionConfig)
• muse_spark — MuseSparkConfig (model MuseSparkConfig)
• muse_spark_audio — MuseSparkAudioConfig (model MuseSparkAudioConfig)
• muse_spark_text — MuseSparkTextConfig (model MuseSparkTextConfig)
• muse_spark_vision — MuseSparkVisionConfig (model MuseSparkVisionConfig)
• musicflamingo — MusicFlamingoConfig (model MusicFlamingoConfig)
• musicgen — MusicgenConfig (model MusicgenConfig)
• musicgen_decoder — MusicgenDecoderConfig (model MusicgenDecoderConfig)
• musicgen_melody — MusicgenMelodyConfig (model MusicgenMelodyConfig)
• musicgen_melody_decoder — MusicgenMelodyDecoderConfig (model MusicgenMelodyDecoderConfig)
• mvp — MvpConfig (model MvpConfig)
• nanochat — NanoChatConfig (model NanoChatConfig)
• nemo_speechlm — Nemotron3_5TranscribeConfig (model Nemotron3_5TranscribeConfig)
• nemotron — NemotronConfig (model NemotronConfig)
• nemotron3_5_asr — Nemotron3_5AsrConfig (model Nemotron3_5AsrConfig)
• nemotron3_5_transcribe_asr_audio — Nemotron3_5TranscribeAsrAudioConfig (model Nemotron3_5TranscribeAsrAudioConfig)
• nemotron3_5_transcribe_audio — Nemotron3_5TranscribeAudioConfig (model Nemotron3_5TranscribeAudioConfig)
• nemotron3_5_transcribe_word_timestamp — Nemotron3_5TranscribeWordTimestampConfig (model Nemotron3_5TranscribeWordTimestampConfig)
• nemotron3_diarization — Nemotron3DiarizationConfig (model Nemotron3DiarizationConfig)
• nemotron3_diarization_audio — Nemotron3DiarizationAudioConfig (model Nemotron3DiarizationAudioConfig)
• nemotron_asr_streaming — NemotronAsrStreamingConfig (model NemotronAsrStreamingConfig)
• nemotron_asr_streaming_encoder — NemotronAsrStreamingEncoderConfig (model NemotronAsrStreamingEncoderConfig)
• nemotron_h — NemotronHConfig (model NemotronHConfig)
• nemotron_h_omni — NemotronH_Omni_Reasoning_V3_Config (model NemotronH_Omni_Reasoning_V3_Config)
• neomme — NeoMMEConfig (model NeoMMEConfig)
• neucodec — NeuCodecConfig (model NeuCodecConfig)
• nllb-moe — NllbMoeConfig (model NllbMoeConfig)
• nomic_bert — NomicBertConfig (model NomicBertConfig)
• nougat — NougatConfig (model NougatConfig)
• nystromformer — NystromformerConfig (model NystromformerConfig)
• olmo — OlmoConfig (model OlmoConfig)
• olmo2 — Olmo2Config (model Olmo2Config)
• olmo3 — Olmo3Config (model Olmo3Config)
• olmo_hybrid — OlmoHybridConfig (model OlmoHybridConfig)
• olmoe — OlmoeConfig (model OlmoeConfig)
• omdet-turbo — OmDetTurboConfig (model OmDetTurboConfig)
• oneformer — OneFormerConfig (model OneFormerConfig)
• openai-gpt — OpenAIGPTConfig (model OpenAIGPTConfig)
• openai_privacy_filter — OpenAIPrivacyFilterConfig (model OpenAIPrivacyFilterConfig)
• opt — OPTConfig (model OPTConfig)
• ovis2 — Ovis2Config (model Ovis2Config)
• ovis2_vision — Ovis2VisionConfig (model Ovis2VisionConfig)
• owlv2 — Owlv2Config (model Owlv2Config)
• owlv2_text_model — Owlv2TextConfig (model Owlv2TextConfig)
• owlv2_vision_model — Owlv2VisionConfig (model Owlv2VisionConfig)
• owlvit — OwlViTConfig (model OwlViTConfig)
• owlvit_text_model — OwlViTTextConfig (model OwlViTTextConfig)
• owlvit_vision_model — OwlViTVisionConfig (model OwlViTVisionConfig)
• paddleocr_vl — PaddleOCRVLConfig (model PaddleOCRVLConfig)
• paddleocr_vl_text — PaddleOCRTextConfig (model PaddleOCRTextConfig)
• paddleocr_vl_vision — PaddleOCRVisionConfig (model PaddleOCRVisionConfig)
• paligemma — PaliGemmaConfig (model PaliGemmaConfig)
• parakeet_ctc — ParakeetCTCConfig (model ParakeetCTCConfig)
• parakeet_encoder — ParakeetEncoderConfig (model ParakeetEncoderConfig)
• parakeet_rnnt — ParakeetRNNTConfig (model ParakeetRNNTConfig)
• parakeet_tdt — ParakeetTDTConfig (model ParakeetTDTConfig)
• patchtsmixer — PatchTSMixerConfig (model PatchTSMixerConfig)
• patchtst — PatchTSTConfig (model PatchTSTConfig)
• pe_audio — PeAudioConfig (model PeAudioConfig)
• pe_audio_encoder — PeAudioEncoderConfig (model PeAudioEncoderConfig)
• pe_audio_video — PeAudioVideoConfig (model PeAudioVideoConfig)
• pe_audio_video_encoder — PeAudioVideoEncoderConfig (model PeAudioVideoEncoderConfig)
• pe_video — PeVideoConfig (model PeVideoConfig)
• pe_video_encoder — PeVideoEncoderConfig (model PeVideoEncoderConfig)
• pegasus — PegasusConfig (model PegasusConfig)
• pegasus_x — PegasusXConfig (model PegasusXConfig)
• perceiver — PerceiverConfig (model PerceiverConfig)
• perception_lm — PerceptionLMConfig (model PerceptionLMConfig)
• persimmon — PersimmonConfig (model PersimmonConfig)
• phi — PhiConfig (model PhiConfig)
• phi3 — Phi3Config (model Phi3Config)
• phi4_multimodal — Phi4MultimodalConfig (model Phi4MultimodalConfig)
• phi4_multimodal_audio — Phi4MultimodalAudioConfig (model Phi4MultimodalAudioConfig)
• phi4_multimodal_vision — Phi4MultimodalVisionConfig (model Phi4MultimodalVisionConfig)
• phimoe — PhimoeConfig (model PhimoeConfig)
• pi0 — PI0Config (model PI0Config)
• pix2struct — Pix2StructConfig (model Pix2StructConfig)
• pix2struct_text_model — Pix2StructTextConfig (model Pix2StructTextConfig)
• pix2struct_vision_model — Pix2StructVisionConfig (model Pix2StructVisionConfig)
• pixio — PixioConfig (model PixioConfig)
• pixtral — PixtralVisionConfig (model PixtralVisionConfig)
• plbart — PLBartConfig (model PLBartConfig)
• pocket_tts — PocketTTSConfig (model PocketTTSConfig)
• pocket_tts_audio_tokenizer — PocketTTSAudioTokenizerConfig (model PocketTTSAudioTokenizerConfig)
• pocket_tts_audio_tokenizer_decoder — PocketTTSAudioTokenizerDecoderConfig (model PocketTTSAudioTokenizerDecoderConfig)
• pocket_tts_audio_tokenizer_encoder — PocketTTSAudioTokenizerEncoderConfig (model PocketTTSAudioTokenizerEncoderConfig)
• poolformer — PoolFormerConfig (model PoolFormerConfig)
• pop2piano — Pop2PianoConfig (model Pop2PianoConfig)
• pp_chart2table — PPChart2TableConfig (model PPChart2TableConfig)
• pp_chart2table_vision — PPChart2TableVisionConfig (model PPChart2TableVisionConfig)
• pp_doclayout_v2 — PPDocLayoutV2Config (model PPDocLayoutV2Config)
• pp_doclayout_v3 — PPDocLayoutV3Config (model PPDocLayoutV3Config)
• pp_doclayout_v4 — PPDocLayoutV4Config (model PPDocLayoutV4Config)
• pp_formulanet — PPFormulaNetConfig (model PPFormulaNetConfig)
• pp_formulanet_text — PPFormulaNetTextConfig (model PPFormulaNetTextConfig)
• pp_formulanet_vision — PPFormulaNetVisionConfig (model PPFormulaNetVisionConfig)
• pp_lcnet — PPLCNetConfig (model PPLCNetConfig)
• pp_lcnet_v3 — PPLCNetV3Config (model PPLCNetV3Config)
• pp_lcnet_v4 — PPLCNetV4Config (model PPLCNetV4Config)
• pp_ocrv5_mobile_det — PPOCRV5MobileDetConfig (model PPOCRV5MobileDetConfig)
• pp_ocrv5_mobile_rec — PPOCRV5MobileRecConfig (model PPOCRV5MobileRecConfig)
• pp_ocrv5_server_det — PPOCRV5ServerDetConfig (model PPOCRV5ServerDetConfig)
• pp_ocrv5_server_rec — PPOCRV5ServerRecConfig (model PPOCRV5ServerRecConfig)
• pp_ocrv6_medium_det — PPOCRV6MediumDetConfig (model PPOCRV6MediumDetConfig)
• pp_ocrv6_small_det — PPOCRV6SmallDetConfig (model PPOCRV6SmallDetConfig)
• pp_ocrv6_small_rec — PPOCRV6SmallRecConfig (model PPOCRV6SmallRecConfig)
• pp_ocrv6_tiny_rec — PPOCRV6TinyRecConfig (model PPOCRV6TinyRecConfig)
• prompt_depth_anything — PromptDepthAnythingConfig (model PromptDepthAnythingConfig)
• prophetnet — ProphetNetConfig (model ProphetNetConfig)
• pvt — PvtConfig (model PvtConfig)
• pvt_v2 — PvtV2Config (model PvtV2Config)
• qianfan_ocr — QianfanOCRConfig (model QianfanOCRConfig)
• qianfan_ocr_vision — QianfanOCRVisionConfig (model QianfanOCRVisionConfig)
• qwen2 — Qwen2Config (model Qwen2Config)
• qwen2_5_omni — Qwen2_5OmniConfig (model Qwen2_5OmniConfig)
• qwen2_5_omni_audio_encoder — Qwen2_5OmniAudioEncoderConfig (model Qwen2_5OmniAudioEncoderConfig)
• qwen2_5_omni_bigvgan — Qwen2_5OmniBigVGANConfig (model Qwen2_5OmniBigVGANConfig)
• qwen2_5_omni_dit — Qwen2_5OmniDiTConfig (model Qwen2_5OmniDiTConfig)
• qwen2_5_omni_talker — Qwen2_5OmniTalkerConfig (model Qwen2_5OmniTalkerConfig)
• qwen2_5_omni_text — Qwen2_5OmniTextConfig (model Qwen2_5OmniTextConfig)
• qwen2_5_omni_thinker — Qwen2_5OmniThinkerConfig (model Qwen2_5OmniThinkerConfig)
• qwen2_5_omni_token2wav — Qwen2_5OmniToken2WavConfig (model Qwen2_5OmniToken2WavConfig)
• qwen2_5_omni_vision_encoder — Qwen2_5OmniVisionEncoderConfig (model Qwen2_5OmniVisionEncoderConfig)
• qwen2_5_vl — Qwen2_5_VLConfig (model Qwen2_5_VLConfig)
• qwen2_5_vl_text — Qwen2_5_VLTextConfig (model Qwen2_5_VLTextConfig)
• qwen2_5_vl_vision — Qwen2_5_VLVisionConfig (model Qwen2_5_VLVisionConfig)
• qwen2_audio — Qwen2AudioConfig (model Qwen2AudioConfig)
• qwen2_audio_encoder — Qwen2AudioEncoderConfig (model Qwen2AudioEncoderConfig)
• qwen2_moe — Qwen2MoeConfig (model Qwen2MoeConfig)
• qwen2_vl — Qwen2VLConfig (model Qwen2VLConfig)
• qwen2_vl_text — Qwen2VLTextConfig (model Qwen2VLTextConfig)
• qwen2_vl_vision — Qwen2VLVisionConfig (model Qwen2VLVisionConfig)
• qwen3 — Qwen3Config (model Qwen3Config)
• qwen3_5 — Qwen3_5Config (model Qwen3_5Config)
• qwen3_5_moe — Qwen3_5MoeConfig (model Qwen3_5MoeConfig)
• qwen3_5_moe_text — Qwen3_5MoeTextConfig (model Qwen3_5MoeTextConfig)
• qwen3_5_moe_vision — Qwen3_5MoeVisionConfig (model Qwen3_5MoeVisionConfig)
• qwen3_5_text — Qwen3_5TextConfig (model Qwen3_5TextConfig)
• qwen3_5_vision — Qwen3_5VisionConfig (model Qwen3_5VisionConfig)
• qwen3_asr — Qwen3ASRConfig (model Qwen3ASRConfig)
• qwen3_asr_encoder — Qwen3ASREncoderConfig (model Qwen3ASREncoderConfig)
• qwen3_moe — Qwen3MoeConfig (model Qwen3MoeConfig)
• qwen3_next — Qwen3NextConfig (model Qwen3NextConfig)
• qwen3_omni_moe — Qwen3OmniMoeConfig (model Qwen3OmniMoeConfig)
• qwen3_omni_moe_audio_encoder — Qwen3OmniMoeAudioEncoderConfig (model Qwen3OmniMoeAudioEncoderConfig)
• qwen3_omni_moe_talker_code_predictor — Qwen3OmniMoeTalkerCodePredictorConfig (model Qwen3OmniMoeTalkerCodePredictorConfig)
• qwen3_omni_moe_talker_text — Qwen3OmniMoeTalkerTextConfig (model Qwen3OmniMoeTalkerTextConfig)
• qwen3_omni_moe_text — Qwen3OmniMoeTextConfig (model Qwen3OmniMoeTextConfig)
• qwen3_omni_moe_thinker — Qwen3OmniMoeThinkerConfig (model Qwen3OmniMoeThinkerConfig)
• qwen3_omni_moe_vision_encoder — Qwen3OmniMoeVisionEncoderConfig (model Qwen3OmniMoeVisionEncoderConfig)
• qwen3_vl — Qwen3VLConfig (model Qwen3VLConfig)
• qwen3_vl_moe — Qwen3VLMoeConfig (model Qwen3VLMoeConfig)
• qwen3_vl_moe_text — Qwen3VLMoeTextConfig (model Qwen3VLMoeTextConfig)
• qwen3_vl_moe_vision — Qwen3VLMoeVisionConfig (model Qwen3VLMoeVisionConfig)
• qwen3_vl_text — Qwen3VLTextConfig (model Qwen3VLTextConfig)
• qwen3_vl_vision — Qwen3VLVisionConfig (model Qwen3VLVisionConfig)
• qwen4_exp — Qwen4ExpConfig (model Qwen4ExpConfig)
• qwen4_exp_text — Qwen4ExpTextConfig (model Qwen4ExpTextConfig)
• qwen4_exp_vision — Qwen4ExpVisionConfig (model Qwen4ExpVisionConfig)
• radio — RadioConfig (model RadioConfig)
• rag — RagConfig (model RagConfig)
• recurrent_gemma — RecurrentGemmaConfig (model RecurrentGemmaConfig)
• reformer — ReformerConfig (model ReformerConfig)
• regnet — RegNetConfig (model RegNetConfig)
• rembert — RemBertConfig (model RemBertConfig)
• resnet — ResNetConfig (model ResNetConfig)
• rf_detr — RfDetrConfig (model RfDetrConfig)
• rf_detr_dinov2 — RfDetrDinov2Config (model RfDetrDinov2Config)
• roberta — RobertaConfig (model RobertaConfig)
• roberta-prelayernorm — RobertaPreLayerNormConfig (model RobertaPreLayerNormConfig)
• roc_bert — RoCBertConfig (model RoCBertConfig)
• roformer — RoFormerConfig (model RoFormerConfig)
• rt_detr — RTDetrConfig (model RTDetrConfig)
• rt_detr_resnet — RTDetrResNetConfig (model RTDetrResNetConfig)
• rt_detr_v2 — RTDetrV2Config (model RTDetrV2Config)
• rwkv — RwkvConfig (model RwkvConfig)
• sam — SamConfig (model SamConfig)
• sam2 — Sam2Config (model Sam2Config)
• sam2_hiera_det_model — Sam2HieraDetConfig (model Sam2HieraDetConfig)
• sam2_mask_decoder — Sam2MaskDecoderConfig (model Sam2MaskDecoderConfig)
• sam2_prompt_encoder — Sam2PromptEncoderConfig (model Sam2PromptEncoderConfig)
• sam2_video — Sam2VideoConfig (model Sam2VideoConfig)
• sam2_video_mask_decoder — Sam2VideoMaskDecoderConfig (model Sam2VideoMaskDecoderConfig)
• sam2_video_prompt_encoder — Sam2VideoPromptEncoderConfig (model Sam2VideoPromptEncoderConfig)
• sam2_vision_model — Sam2VisionConfig (model Sam2VisionConfig)
• sam3 — Sam3Config (model Sam3Config)
• sam3_detr_decoder — Sam3DETRDecoderConfig (model Sam3DETRDecoderConfig)
• sam3_detr_encoder — Sam3DETREncoderConfig (model Sam3DETREncoderConfig)
• sam3_geometry_encoder — Sam3GeometryEncoderConfig (model Sam3GeometryEncoderConfig)
• sam3_lite_text — Sam3LiteTextConfig (model Sam3LiteTextConfig)
• sam3_lite_text_detr_decoder — Sam3LiteTextDETRDecoderConfig (model Sam3LiteTextDETRDecoderConfig)
• sam3_lite_text_detr_encoder — Sam3LiteTextDETREncoderConfig (model Sam3LiteTextDETREncoderConfig)
• sam3_lite_text_geometry_encoder — Sam3LiteTextGeometryEncoderConfig (model Sam3LiteTextGeometryEncoderConfig)
• sam3_lite_text_mask_decoder — Sam3LiteTextMaskDecoderConfig (model Sam3LiteTextMaskDecoderConfig)
• sam3_lite_text_text_model — Sam3LiteTextTextConfig (model Sam3LiteTextTextConfig)
• sam3_mask_decoder — Sam3MaskDecoderConfig (model Sam3MaskDecoderConfig)
• sam3_tracker — Sam3TrackerConfig (model Sam3TrackerConfig)
• sam3_tracker_mask_decoder — Sam3TrackerMaskDecoderConfig (model Sam3TrackerMaskDecoderConfig)
• sam3_tracker_prompt_encoder — Sam3TrackerPromptEncoderConfig (model Sam3TrackerPromptEncoderConfig)
• sam3_tracker_video — Sam3TrackerVideoConfig (model Sam3TrackerVideoConfig)
• sam3_tracker_video_mask_decoder — Sam3TrackerVideoMaskDecoderConfig (model Sam3TrackerVideoMaskDecoderConfig)
• sam3_tracker_video_prompt_encoder — Sam3TrackerVideoPromptEncoderConfig (model Sam3TrackerVideoPromptEncoderConfig)
• sam3_video — Sam3VideoConfig (model Sam3VideoConfig)
• sam3_vision_model — Sam3VisionConfig (model Sam3VisionConfig)
• sam3_vit_model — Sam3ViTConfig (model Sam3ViTConfig)
• sam_hq — SamHQConfig (model SamHQConfig)
• sam_hq_mask_decoder — SamHQMaskDecoderConfig (model SamHQMaskDecoderConfig)
• sam_hq_prompt_encoder — SamHQPromptEncoderConfig (model SamHQPromptEncoderConfig)
• sam_hq_vision_model — SamHQVisionConfig (model SamHQVisionConfig)
• sam_mask_decoder — SamMaskDecoderConfig (model SamMaskDecoderConfig)
• sam_prompt_encoder — SamPromptEncoderConfig (model SamPromptEncoderConfig)
• sam_vision_model — SamVisionConfig (model SamVisionConfig)
• sapiens2 — Sapiens2Config (model Sapiens2Config)
• sapiens2_head — Sapiens2HeadConfig (model Sapiens2HeadConfig)
• seamless_m4t — SeamlessM4TConfig (model SeamlessM4TConfig)
• seamless_m4t_v2 — SeamlessM4Tv2Config (model SeamlessM4Tv2Config)
• seed_oss — SeedOssConfig (model SeedOssConfig)
• segformer — SegformerConfig (model SegformerConfig)
• seggpt — SegGptConfig (model SegGptConfig)
• sew — SEWConfig (model SEWConfig)
• sew-d — SEWDConfig (model SEWDConfig)
• shieldgemma2 — ShieldGemma2Config (model ShieldGemma2Config)
• siglip — SiglipConfig (model SiglipConfig)
• siglip2 — Siglip2Config (model Siglip2Config)
• siglip2_text_model — Siglip2TextConfig (model Siglip2TextConfig)
• siglip2_vision_model — Siglip2VisionConfig (model Siglip2VisionConfig)
• siglip_text_model — SiglipTextConfig (model SiglipTextConfig)
• siglip_vision_model — SiglipVisionConfig (model SiglipVisionConfig)
• slanet — SLANetConfig (model SLANetConfig)
• slanext — SLANeXtConfig (model SLANeXtConfig)
• slanext_vision — SLANeXtVisionConfig (model SLANeXtVisionConfig)
• smollm3 — SmolLM3Config (model SmolLM3Config)
• smolvlm — SmolVLMConfig (model SmolVLMConfig)
• smolvlm_vision — SmolVLMVisionConfig (model SmolVLMVisionConfig)
• solar_open — SolarOpenConfig (model SolarOpenConfig)
• speech-encoder-decoder — SpeechEncoderDecoderConfig (model SpeechEncoderDecoderConfig)
• speech_to_text — Speech2TextConfig (model Speech2TextConfig)
• speecht5 — SpeechT5Config (model SpeechT5Config)
• speecht5_hifigan — SpeechT5HifiGanConfig (model SpeechT5HifiGanConfig)
• splinter — SplinterConfig (model SplinterConfig)
• squeezebert — SqueezeBertConfig (model SqueezeBertConfig)
• stablelm — StableLmConfig (model StableLmConfig)
• starcoder2 — Starcoder2Config (model Starcoder2Config)
• step3p5 — Step3p7TextConfig (model Step3p7TextConfig)
• step3p5_vision — Step3p7VisionConfig (model Step3p7VisionConfig)
• step3p7 — Step3p7Config (model Step3p7Config)
• superglue — SuperGlueConfig (model SuperGlueConfig)
• superpoint — SuperPointConfig (model SuperPointConfig)
• swiftformer — SwiftFormerConfig (model SwiftFormerConfig)
• swin — SwinConfig (model SwinConfig)
• swin2sr — Swin2SRConfig (model Swin2SRConfig)
• swinv2 — Swinv2Config (model Swinv2Config)
• switch_transformers — SwitchTransformersConfig (model SwitchTransformersConfig)
• t5 — T5Config (model T5Config)
• t5_gemma_module — T5GemmaModuleConfig (model T5GemmaModuleConfig)
• t5gemma — T5GemmaConfig (model T5GemmaConfig)
• t5gemma2 — T5Gemma2Config (model T5Gemma2Config)
• t5gemma2_decoder — T5Gemma2DecoderConfig (model T5Gemma2DecoderConfig)
• t5gemma2_encoder — T5Gemma2EncoderConfig (model T5Gemma2EncoderConfig)
• t5gemma2_text — T5Gemma2TextConfig (model T5Gemma2TextConfig)
• table-transformer — TableTransformerConfig (model TableTransformerConfig)
• tapas — TapasConfig (model TapasConfig)
• textnet — TextNetConfig (model TextNetConfig)
• time_series_transformer — TimeSeriesTransformerConfig (model TimeSeriesTransformerConfig)
• timesfm — TimesFmConfig (model TimesFmConfig)
• timesfm2_5 — TimesFm2_5Config (model TimesFm2_5Config)
• timesformer — TimesformerConfig (model TimesformerConfig)
• timm_backbone — TimmBackboneConfig (model TimmBackboneConfig)
• timm_wrapper — TimmWrapperConfig (model TimmWrapperConfig)
• tipsv2 — Tipsv2Config (model Tipsv2Config)
• tipsv2_dpt — Tipsv2DptConfig (model Tipsv2DptConfig)
• tipsv2_text_model — Tipsv2TextConfig (model Tipsv2TextConfig)
• tipsv2_vision_model — Tipsv2VisionConfig (model Tipsv2VisionConfig)
• trocr — TrOCRConfig (model TrOCRConfig)
• tvp — TvpConfig (model TvpConfig)
• udop — UdopConfig (model UdopConfig)
• ultrabert — UltrabertConfig (model UltrabertConfig)
• ultravbert — UltraVBertConfig (model UltraVBertConfig)
• umt5 — UMT5Config (model UMT5Config)
• unispeech — UniSpeechConfig (model UniSpeechConfig)
• unispeech-sat — UniSpeechSatConfig (model UniSpeechSatConfig)
• univnet — UnivNetConfig (model UnivNetConfig)
• unlimited_ocr — UnlimitedOcrConfig (model UnlimitedOcrConfig)
• unlimited_ocr_sam_vision_model — UnlimitedOcrSamVisionConfig (model UnlimitedOcrSamVisionConfig)
• unlimited_ocr_text — UnlimitedOcrTextConfig (model UnlimitedOcrTextConfig)
• unlimited_ocr_vision — UnlimitedOcrVisionConfig (model UnlimitedOcrVisionConfig)
• unlimited_ocr_vision_encoder — UnlimitedOcrVisionEncoderConfig (model UnlimitedOcrVisionEncoderConfig)
• upernet — UperNetConfig (model UperNetConfig)
• uvdoc — UVDocConfig (model UVDocConfig)
• uvdoc_backbone — UVDocBackboneConfig (model UVDocBackboneConfig)
• vaultgemma — VaultGemmaConfig (model VaultGemmaConfig)
• vibevoice — VibeVoiceConfig (model VibeVoiceConfig)
• vibevoice_acoustic_tokenizer — VibeVoiceAcousticTokenizerConfig (model VibeVoiceAcousticTokenizerConfig)
• vibevoice_acoustic_tokenizer_decoder — VibeVoiceAcousticTokenizerDecoderConfig (model VibeVoiceAcousticTokenizerDecoderConfig)
• vibevoice_acoustic_tokenizer_encoder — VibeVoiceAcousticTokenizerEncoderConfig (model VibeVoiceAcousticTokenizerEncoderConfig)
• vibevoice_asr — VibeVoiceAsrConfig (model VibeVoiceAsrConfig)
• vibevoice_diffusion — VibeVoiceDiffusionHeadConfig (model VibeVoiceDiffusionHeadConfig)
• video_llama_3 — VideoLlama3Config (model VideoLlama3Config)
• video_llama_3_vision — VideoLlama3VisionConfig (model VideoLlama3VisionConfig)
• video_llava — VideoLlavaConfig (model VideoLlavaConfig)
• videomae — VideoMAEConfig (model VideoMAEConfig)
• videomt — VideomtConfig (model VideomtConfig)
• videoprism — VideoPrismConfig (model VideoPrismConfig)
• videoprism_text_model — VideoPrismTextConfig (model VideoPrismTextConfig)
• videoprism_vision_model — VideoPrismVisionConfig (model VideoPrismVisionConfig)
• vilt — ViltConfig (model ViltConfig)
• vipllava — VipLlavaConfig (model VipLlavaConfig)
• vision-encoder-decoder — VisionEncoderDecoderConfig (model VisionEncoderDecoderConfig)
• vision-text-dual-encoder — VisionTextDualEncoderConfig (model VisionTextDualEncoderConfig)
• visual_bert — VisualBertConfig (model VisualBertConfig)
• vit — ViTConfig (model ViTConfig)
• vit_mae — ViTMAEConfig (model ViTMAEConfig)
• vit_msn — ViTMSNConfig (model ViTMSNConfig)
• vitdet — VitDetConfig (model VitDetConfig)
• vitmatte — VitMatteConfig (model VitMatteConfig)
• vitpose — VitPoseConfig (model VitPoseConfig)
• vitpose_backbone — VitPoseBackboneConfig (model VitPoseBackboneConfig)
• vits — VitsConfig (model VitsConfig)
• vivit — VivitConfig (model VivitConfig)
• vjepa2 — VJEPA2Config (model VJEPA2Config)
• voxtral — VoxtralConfig (model VoxtralConfig)
• voxtral_encoder — VoxtralEncoderConfig (model VoxtralEncoderConfig)
• voxtral_realtime — VoxtralRealtimeConfig (model VoxtralRealtimeConfig)
• voxtral_realtime_encoder — VoxtralRealtimeEncoderConfig (model VoxtralRealtimeEncoderConfig)
• voxtral_realtime_text — VoxtralRealtimeTextConfig (model VoxtralRealtimeTextConfig)
• wav2vec2 — Wav2Vec2Config (model Wav2Vec2Config)
• wav2vec2-bert — Wav2Vec2BertConfig (model Wav2Vec2BertConfig)
• wav2vec2-conformer — Wav2Vec2ConformerConfig (model Wav2Vec2ConformerConfig)
• wavlm — WavLMConfig (model WavLMConfig)
• whisper — WhisperConfig (model WhisperConfig)
• xclip — XCLIPConfig (model XCLIPConfig)
• xclip_text_model — XCLIPTextConfig (model XCLIPTextConfig)
• xclip_vision_model — XCLIPVisionConfig (model XCLIPVisionConfig)
• xcodec — XcodecConfig (model XcodecConfig)
• xcodec2 — Xcodec2Config (model Xcodec2Config)
• xglm — XGLMConfig (model XGLMConfig)
• xlm — XLMConfig (model XLMConfig)
• xlm-roberta — XLMRobertaConfig (model XLMRobertaConfig)
• xlm-roberta-xl — XLMRobertaXLConfig (model XLMRobertaXLConfig)
• xlnet — XLNetConfig (model XLNetConfig)
• xlstm — xLSTMConfig (model xLSTMConfig)
• xmod — XmodConfig (model XmodConfig)
• yolos — YolosConfig (model YolosConfig)
• yoso — YosoConfig (model YosoConfig)
• youtu — YoutuConfig (model YoutuConfig)
• zamba — ZambaConfig (model ZambaConfig)
• zamba2 — Zamba2Config (model Zamba2Config)
• zaya — ZayaConfig (model ZayaConfig)
• zoedepth — ZoeDepthConfig (model ZoeDepthConfig)

>>> from transformers import AutoConfig

>>> # Download configuration from huggingface.co and cache.
>>> config = AutoConfig.from_pretrained("google-bert/bert-base-uncased")

>>> # Download configuration from huggingface.co (user-uploaded) and cache.
>>> config = AutoConfig.from_pretrained("dbmdz/bert-base-german-cased")

>>> # If configuration file is in a directory (e.g., was saved using *save_pretrained('./test/saved_model/')*).
>>> config = AutoConfig.from_pretrained("./test/bert_saved_model/")

>>> # Load a specific configuration file.
>>> config = AutoConfig.from_pretrained("./test/bert_saved_model/my_configuration.json")

>>> # Change some config attributes when loading a pretrained config.
>>> config = AutoConfig.from_pretrained("google-bert/bert-base-uncased", output_attentions=True, foo=False)
>>> config.output_attentions
True

>>> config, unused_kwargs = AutoConfig.from_pretrained(
...     "google-bert/bert-base-uncased", output_attentions=True, foo=False, return_unused_kwargs=True
... )
>>> config.output_attentions
True

>>> unused_kwargs
{'foo': False}

Daftarkan konfigurasi baru untuk kelas ini.

Instansiasi salah satu kelas tokenizer dari pustaka ini dari kosakata model terlatih sebelumnya.

Kelas tokenizer yang akan diinstansiasi dipilih berdasarkan properti model_type dari objek config (baik yang dilewatkan sebagai argumen maupun dimuat dari pretrained_model_name_or_path jika memungkinkan), atau jika properti tersebut tidak ada, dengan menggunakan pencocokan pola pada pretrained_model_name_or_path:

• EvollaModel — TokenizersBackend (model EvollaConfig)
• aimv2 — CLIPTokenizer (model Aimv2Config)
• albert — AlbertTokenizer (model AlbertConfig)
• align — BertTokenizer (model AlignConfig)
• aria — TokenizersBackend (model AriaConfig)
• audioflamingo3 — Qwen2Tokenizer (model AudioFlamingo3Config)
• aya_vision — CohereTokenizer (model AyaVisionConfig)
• bark — BertTokenizer (model BarkConfig)
• bart — RobertaTokenizer (model BartConfig)
• beam — TokenizersBackend (model BeamConfig)
• bert — BertTokenizer (model BertConfig)
• bert-generation — BertGenerationTokenizer (model BertGenerationConfig)
• big_bird — BigBirdTokenizer (model BigBirdConfig)
• bigbird_pegasus — TokenizersBackend (model BigBirdPegasusConfig)
• biogpt — BioGptTokenizer (model BioGptConfig)
• blenderbot — BlenderbotTokenizer (model BlenderbotConfig)
• blenderbot-small — BlenderbotSmallTokenizer (model BlenderbotSmallConfig)
• blip — BertTokenizer (model BlipConfig)
• blip-2 — GPT2Tokenizer (model Blip2Config)
• bridgetower — RobertaTokenizer (model BridgeTowerConfig)
• bros — BertTokenizer (model BrosConfig)
• camembert — CamembertTokenizer (model CamembertConfig)
• canary — TokenizersBackend (model CanaryConfig)
• canine — CanineTokenizer (model CanineConfig)
• chinese_clip — BertTokenizer (model ChineseCLIPConfig)
• clap — RobertaTokenizer (model ClapConfig)
• clip — CLIPTokenizer (model CLIPConfig)
• clipseg — CLIPTokenizer (model CLIPSegConfig)
• clvp — ClvpTokenizer (model ClvpConfig)
• codegen — GPT2Tokenizer (model CodeGenConfig)
• cohere — CohereTokenizer (model CohereConfig)
• cohere2 — CohereTokenizer (model Cohere2Config)
• cohere_asr — TokenizersBackend (model CohereAsrConfig)
• colqwen2 — Qwen2Tokenizer (model ColQwen2Config)
• convbert — BertTokenizer (model ConvBertConfig)
• cosmos3_omni — Qwen2Tokenizer (model Cosmos3OmniConfig)
• cpmant — CpmAntTokenizer (model CpmAntConfig)
• ctrl — CTRLTokenizer (model CTRLConfig)
• data2vec-audio — Wav2Vec2CTCTokenizer (model Data2VecAudioConfig)
• data2vec-text — RobertaTokenizer (model Data2VecTextConfig)
• dbrx — GPT2Tokenizer (model DbrxConfig)
• deberta — DebertaTokenizer (model DebertaConfig)
• deberta-v2 — DebertaV2Tokenizer (model DebertaV2Config)
• dia — DiaTokenizer (model DiaConfig)
• diffusion_gemma — GemmaTokenizer (model DiffusionGemmaConfig)
• distilbert — BertTokenizer (model DistilBertConfig)
• dpr — DPRQuestionEncoderTokenizer (model DPRConfig)
• electra — BertTokenizer (model ElectraConfig)
• emu3 — GPT2Tokenizer (model Emu3Config)
• ernie — BertTokenizer (model ErnieConfig)
• ernie4_5 — TokenizersBackend (model Ernie4_5Config)
• ernie4_5_moe — TokenizersBackend (model Ernie4_5_MoeConfig)
• esm — EsmTokenizer (model EsmConfig)
• esmc — EsmcTokenizer (model EsmcConfig)
• esmfold2 — EsmcTokenizer (model EsmFold2Config)
• falcon_mamba — GPTNeoXTokenizer (model FalconMambaConfig)
• fastspeech2_conformer — None (model FastSpeech2ConformerConfig)
• flaubert — FlaubertTokenizer (model FlaubertConfig)
• flava — BertTokenizer (model FlavaConfig)
• flex_olmo — TokenizersBackend (model FlexOlmoConfig)
• florence2 — BartTokenizer (model Florence2Config)
• fnet — FNetTokenizer (model FNetConfig)
• fsmt — FSMTTokenizer (model FSMTConfig)
• fun_asr_nano — Qwen2Tokenizer (model FunAsrNanoConfig)
• funnel — FunnelTokenizer (model FunnelConfig)
• fuyu — TokenizersBackend (model FuyuConfig)
• gemma — GemmaTokenizer (model GemmaConfig)
• gemma2 — GemmaTokenizer (model Gemma2Config)
• gemma3 — GemmaTokenizer (model Gemma3Config)
• gemma3_text — GemmaTokenizer (model Gemma3TextConfig)
• gemma3n — GemmaTokenizer (model Gemma3nConfig)
• gemma3n_text — GemmaTokenizer (model Gemma3nTextConfig)
• git — BertTokenizer (model GitConfig)
• glm — TokenizersBackend (model GlmConfig)
• glm4 — TokenizersBackend (model Glm4Config)
• glm4_moe — TokenizersBackend (model Glm4MoeConfig)
• glm4_moe_lite — TokenizersBackend (model Glm4MoeLiteConfig)
• glm4v — TokenizersBackend (model Glm4vConfig)
• glm4v_moe — TokenizersBackend (model Glm4vMoeConfig)
• glm_image — TokenizersBackend (model GlmImageConfig)
• glmasr — TokenizersBackend (model GlmAsrConfig)
• got_ocr2 — TokenizersBackend (model GotOcr2Config)
• gpt-sw3 — GPTSw3Tokenizer (model GPT2Config)
• gpt2 — GPT2Tokenizer (model GPT2Config)
• gpt_bigcode — TokenizersBackend (model GPTBigCodeConfig)
• gpt_neo — GPT2Tokenizer (model GPTNeoConfig)
• gpt_neox — GPTNeoXTokenizer (model GPTNeoXConfig)
• gpt_neox_japanese — GPTNeoXJapaneseTokenizer (model GPTNeoXJapaneseConfig)
• gptj — GPT2Tokenizer (model GPTJConfig)
• gradium_phonon_tts — TokenizersBackend (model GradiumPhononTTSConfig)
• granite — TokenizersBackend (model GraniteConfig)
• granite_speech5_ctc — ParakeetTokenizer (model GraniteSpeech5CTCConfig)
• granitemoe — TokenizersBackend (model GraniteMoeConfig)
• granitemoehybrid — TokenizersBackend (model GraniteMoeHybridConfig)
• granitemoeshared — TokenizersBackend (model GraniteMoeSharedConfig)
• grounding-dino — BertTokenizer (model GroundingDinoConfig)
• groupvit — CLIPTokenizer (model GroupViTConfig)
• gte — XLMRobertaTokenizer (model GteConfig)
• hubert — Wav2Vec2CTCTokenizer (model HubertConfig)
• hunyuan_vl — Qwen2Tokenizer (model HunYuanVLConfig)
• hyperclovax — TokenizersBackend (model HyperCLOVAXConfig)
• hyperclovax_vision_v2 — GPT2Tokenizer (model HyperCLOVAXVisionV2Config)
• ibert — RobertaTokenizer (model IBertConfig)
• idefics — LlamaTokenizer (model IdeficsConfig)
• idefics2 — LlamaTokenizer (model Idefics2Config)
• instructblip — GPT2Tokenizer (model InstructBlipConfig)
• instructblipvideo — GPT2Tokenizer (model InstructBlipVideoConfig)
• internvl — Qwen2Tokenizer (model InternVLConfig)
• jais2 — GPT2Tokenizer (model Jais2Config)
• jamba — TokenizersBackend (model JambaConfig)
• jina_embeddings_v3 — XLMRobertaTokenizer (model JinaEmbeddingsV3Config)
• kimi_k25 — TokenizersBackend (model Kimi_K25Config)
• kimi_linear — TokenizersBackend (model KimiLinearConfig)
• kosmos-2 — TokenizersBackend (model Kosmos2Config)
• lasr_ctc — LasrTokenizer (model LasrCTCConfig)
• lasr_encoder — LasrTokenizer (model LasrEncoderConfig)
• layoutlm — BertTokenizer (model LayoutLMConfig)
• layoutlmv2 — LayoutLMv2Tokenizer (model LayoutLMv2Config)
• layoutlmv3 — LayoutLMv3Tokenizer (model LayoutLMv3Config)
• layoutxlm — LayoutXLMTokenizer (model LayoutXLMConfig)
• led — LEDTokenizer (model LEDConfig)
• lighton_ocr — Qwen2TokenizerFast (model LightOnOcrConfig)
• lilt — RobertaTokenizer (model LiltConfig)
• llava — TokenizersBackend (model LlavaConfig)
• llava_next — TokenizersBackend (model LlavaNextConfig)
• longformer — RobertaTokenizer (model LongformerConfig)
• luke — LukeTokenizer (model LukeConfig)
• lxmert — LxmertTokenizer (model LxmertConfig)
• m2m_100 — M2M100Tokenizer (model M2M100Config)
• mamba — GPTNeoXTokenizer (model MambaConfig)
• mamba2 — GPTNeoXTokenizer (model Mamba2Config)
• marian — MarianTokenizer (model MarianConfig)
• markuplm — MarkupLMTokenizer (model MarkupLMConfig)
• mbart — MBartTokenizer (model MBartConfig)
• megatron-bert — BertTokenizer (model MegatronBertConfig)
• metaclip_2 — XLMRobertaTokenizer (model MetaClip2Config)
• mgp-str — MgpstrTokenizer (model MgpstrConfig)
• mimo_v2_flash — TokenizersBackend (model MiMoV2FlashConfig)
• minicpm3 — TokenizersBackend (model MiniCPM3Config)
• minicpm_ocr — TokenizersBackend (model MiniCPMOcrConfig)
• minicpmv4_6 — TokenizersBackend (model MiniCPMV4_6Config)
• minicpmv4_7 — TokenizersBackend (model MiniCPMV4_7Config)
• minimax_m2 — TokenizersBackend (model MiniMaxM2Config)
• ministral — MistralCommonBackend (model MinistralConfig)
• ministral3 — MistralCommonBackend (model Ministral3Config)
• mistral — MistralCommonBackend (model MistralConfig)
• mistral3 — MistralCommonBackend (model Mistral3Config)
• mistral_large4 — MistralCommonBackend (model MistralLarge4Config)
• mixtral — MistralCommonBackend (model MixtralConfig)
• mm-grounding-dino — BertTokenizer (model MMGroundingDinoConfig)
• mobilebert — MobileBertTokenizer (model MobileBertConfig)
• modernbert — TokenizersBackend (model ModernBertConfig)
• modernbert-decoder — TokenizersBackend (model ModernBertDecoderConfig)
• molmo2 — TokenizersBackend (model Molmo2Config)
• moss_transcribe_diarize — Qwen2Tokenizer (model MossTranscribeDiarizeConfig)
• mpnet — MPNetTokenizer (model MPNetConfig)
• mpt — GPTNeoXTokenizer (model MptConfig)
• mra — RobertaTokenizer (model MraConfig)
• mt5 — T5Tokenizer (model MT5Config)
• musicgen — T5Tokenizer (model MusicgenConfig)
• musicgen_melody — T5Tokenizer (model MusicgenMelodyConfig)
• mvp — MvpTokenizer (model MvpConfig)
• nemo_speechlm — TokenizersBackend (model Nemotron3_5TranscribeConfig)
• nemotron — TokenizersBackend (model NemotronConfig)
• nemotron3_5_asr — ParakeetTokenizer (model Nemotron3_5AsrConfig)
• nemotron_asr_streaming — ParakeetTokenizer (model NemotronAsrStreamingConfig)
• nllb-moe — NllbTokenizer (model NllbMoeConfig)
• nomic_bert — BertTokenizer (model NomicBertConfig)
• nougat — NougatTokenizer (model NougatConfig)
• nystromformer — TokenizersBackend (model NystromformerConfig)
• olmo — GPTNeoXTokenizer (model OlmoConfig)
• olmo2 — TokenizersBackend (model Olmo2Config)
• olmo3 — TokenizersBackend (model Olmo3Config)
• olmo_hybrid — TokenizersBackend (model OlmoHybridConfig)
• olmoe — GPTNeoXTokenizer (model OlmoeConfig)
• omdet-turbo — CLIPTokenizer (model OmDetTurboConfig)
• oneformer — CLIPTokenizer (model OneFormerConfig)
• openai-gpt — OpenAIGPTTokenizer (model OpenAIGPTConfig)
• opt — GPT2Tokenizer (model OPTConfig)
• ovis2 — Qwen2Tokenizer (model Ovis2Config)
• owlv2 — CLIPTokenizer (model Owlv2Config)
• owlvit — CLIPTokenizer (model OwlViTConfig)
• paddleocr_vl — TokenizersBackend (model PaddleOCRVLConfig)
• parakeet_ctc — ParakeetTokenizer (model ParakeetCTCConfig)
• parakeet_rnnt — ParakeetTokenizer (model ParakeetRNNTConfig)
• parakeet_tdt — ParakeetTokenizer (model ParakeetTDTConfig)
• pegasus — PegasusTokenizer (model PegasusConfig)
• pegasus_x — TokenizersBackend (model PegasusXConfig)
• perceiver — PerceiverTokenizer (model PerceiverConfig)
• persimmon — TokenizersBackend (model PersimmonConfig)
• phi — GPT2Tokenizer (model PhiConfig)
• phi3 — TokenizersBackend (model Phi3Config)
• phimoe — TokenizersBackend (model PhimoeConfig)
• pix2struct — TokenizersBackend (model Pix2StructConfig)
• pixtral — MistralCommonBackend (model PixtralVisionConfig)
• plbart — PLBartTokenizer (model PLBartConfig)
• pocket_tts — TokenizersBackend (model PocketTTSConfig)
• pp_formulanet — NougatTokenizer (model PPFormulaNetConfig)
• prophetnet — ProphetNetTokenizer (model ProphetNetConfig)
• qianfan_ocr — Qwen2Tokenizer (model QianfanOCRConfig)
• qwen2 — Qwen2Tokenizer (model Qwen2Config)
• qwen2_5_omni — Qwen2Tokenizer (model Qwen2_5OmniConfig)
• qwen2_5_vl — Qwen2Tokenizer (model Qwen2_5_VLConfig)
• qwen2_audio — Qwen2Tokenizer (model Qwen2AudioConfig)
• qwen2_moe — Qwen2Tokenizer (model Qwen2MoeConfig)
• qwen2_vl — Qwen2Tokenizer (model Qwen2VLConfig)
• qwen3 — Qwen2Tokenizer (model Qwen3Config)
• qwen3_5 — Qwen3_5Tokenizer (model Qwen3_5Config)
• qwen3_5_moe — Qwen3_5Tokenizer (model Qwen3_5MoeConfig)
• qwen3_5_moe_text — Qwen3_5Tokenizer (model Qwen3_5MoeTextConfig)
• qwen3_5_text — Qwen3_5Tokenizer (model Qwen3_5TextConfig)
• qwen3_asr — Qwen2Tokenizer (model Qwen3ASRConfig)
• qwen3_moe — Qwen2Tokenizer (model Qwen3MoeConfig)
• qwen3_next — Qwen2Tokenizer (model Qwen3NextConfig)
• qwen3_omni_moe — Qwen2Tokenizer (model Qwen3OmniMoeConfig)
• qwen3_vl — Qwen2Tokenizer (model Qwen3VLConfig)
• qwen3_vl_moe — Qwen2Tokenizer (model Qwen3VLMoeConfig)
• qwen4_exp — Qwen3_5Tokenizer (model Qwen4ExpConfig)
• rag — RagTokenizer (model RagConfig)
• recurrent_gemma — GemmaTokenizer (model RecurrentGemmaConfig)
• reformer — ReformerTokenizer (model ReformerConfig)
• rembert — RemBertTokenizer (model RemBertConfig)
• roberta — RobertaTokenizer (model RobertaConfig)
• roberta-prelayernorm — RobertaTokenizer (model RobertaPreLayerNormConfig)
• roc_bert — RoCBertTokenizer (model RoCBertConfig)
• roformer — RoFormerTokenizer (model RoFormerConfig)
• rwkv — GPTNeoXTokenizer (model RwkvConfig)
• sam3 — CLIPTokenizer (model Sam3Config)
• sam3_video — CLIPTokenizer (model Sam3VideoConfig)
• seamless_m4t — SeamlessM4TTokenizer (model SeamlessM4TConfig)
• seamless_m4t_v2 — SeamlessM4TTokenizer (model SeamlessM4Tv2Config)
• shieldgemma2 — GemmaTokenizer (model ShieldGemma2Config)
• siglip — SiglipTokenizer (model SiglipConfig)
• siglip2 — Siglip2Tokenizer (model Siglip2Config)
• smolvlm — TokenizersBackend (model SmolVLMConfig)
• speech_to_text — Speech2TextTokenizer (model Speech2TextConfig)
• speecht5 — SpeechT5Tokenizer (model SpeechT5Config)
• splinter — SplinterTokenizer (model SplinterConfig)
• squeezebert — BertTokenizer (model SqueezeBertConfig)
• stablelm — TokenizersBackend (model StableLmConfig)
• starcoder2 — GPT2Tokenizer (model Starcoder2Config)
• switch_transformers — T5Tokenizer (model SwitchTransformersConfig)
• t5 — T5Tokenizer (model T5Config)
• t5gemma — GemmaTokenizer (model T5GemmaConfig)
• tapas — TapasTokenizer (model TapasConfig)
• tipsv2 — Tipsv2Tokenizer (model Tipsv2Config)
• trocr — XLMRobertaTokenizer (model TrOCRConfig)
• tvp — BertTokenizer (model TvpConfig)
• udop — UdopTokenizer (model UdopConfig)
• umt5 — TokenizersBackend (model UMT5Config)
• unispeech — Wav2Vec2CTCTokenizer (model UniSpeechConfig)
• unispeech-sat — Wav2Vec2CTCTokenizer (model UniSpeechSatConfig)
• vibevoice — Qwen2TokenizerFast (model VibeVoiceConfig)
• videoprism — VideoPrismTokenizer (model VideoPrismConfig)
• vilt — BertTokenizer (model ViltConfig)
• vipllava — TokenizersBackend (model VipLlavaConfig)
• visual_bert — BertTokenizer (model VisualBertConfig)
• vits — VitsTokenizer (model VitsConfig)
• voxtral — MistralCommonBackend (model VoxtralConfig)
• voxtral_realtime — MistralCommonBackend (model VoxtralRealtimeConfig)
• wav2vec2 — Wav2Vec2CTCTokenizer (model Wav2Vec2Config)
• wav2vec2-bert — Wav2Vec2CTCTokenizer (model Wav2Vec2BertConfig)
• wav2vec2-conformer — Wav2Vec2CTCTokenizer (model Wav2Vec2ConformerConfig)
• whisper — WhisperTokenizer (model WhisperConfig)
• xclip — CLIPTokenizer (model XCLIPConfig)
• xglm — XGLMTokenizer (model XGLMConfig)
• xlm — XLMTokenizer (model XLMConfig)
• xlm-roberta — XLMRobertaTokenizer (model XLMRobertaConfig)
• xlm-roberta-xl — TokenizersBackend (model XLMRobertaXLConfig)
• xlnet — XLNetTokenizer (model XLNetConfig)
• xlstm — GPTNeoXTokenizer (model xLSTMConfig)
• xmod — XLMRobertaTokenizer (model XmodConfig)
• yoso — AlbertTokenizer (model YosoConfig)
• zaya — GemmaTokenizer (model ZayaConfig)

>>> from transformers import AutoTokenizer

>>> # Download vocabulary from huggingface.co and cache.
>>> tokenizer = AutoTokenizer.from_pretrained("google-bert/bert-base-uncased")

>>> # Download vocabulary from huggingface.co (user-uploaded) and cache.
>>> tokenizer = AutoTokenizer.from_pretrained("dbmdz/bert-base-german-cased")

>>> # If vocabulary files are in a directory (e.g. tokenizer was saved using *save_pretrained('./test/saved_model/')*)
>>> # tokenizer = AutoTokenizer.from_pretrained("./test/bert_saved_model/")

>>> # Download vocabulary from huggingface.co and define model-specific arguments
>>> tokenizer = AutoTokenizer.from_pretrained("FacebookAI/roberta-base", add_prefix_space=True)

Daftarkan tokenizer baru dalam pemetaan ini.

Instansiasi salah satu kelas feature extractor dari pustaka ini dari kosakata model pretrained.

Kelas feature extractor yang akan diinstansiasi dipilih berdasarkan properti model_type dari objek config (yang diberikan sebagai argumen atau dimuat dari pretrained_model_name_or_path jika memungkinkan), atau jika properti tersebut tidak ada, dengan menggunakan pattern matching pada pretrained_model_name_or_path:

• audio-spectrogram-transformer — ASTFeatureExtractor (model ASTConfig)
• audioflamingo3 — WhisperFeatureExtractor (model AudioFlamingo3Config)
• canary — ParakeetFeatureExtractor (model CanaryConfig)
• clap — ClapFeatureExtractor (model ClapConfig)
• clvp — ClvpFeatureExtractor (model ClvpConfig)
• cohere_asr — CohereAsrFeatureExtractor (model CohereAsrConfig)
• csm — EncodecFeatureExtractor (model CsmConfig)
• dac — DacFeatureExtractor (model DacConfig)
• data2vec-audio — Wav2Vec2FeatureExtractor (model Data2VecAudioConfig)
• dia — DiaFeatureExtractor (model DiaConfig)
• embedding_gemma2 — Gemma4AudioFeatureExtractor (model EmbeddingGemma2Config)
• encodec — EncodecFeatureExtractor (model EncodecConfig)
• fun_asr_nano — FunAsrNanoFeatureExtractor (model FunAsrNanoConfig)
• gemma3n — Gemma3nAudioFeatureExtractor (model Gemma3nConfig)
• gemma4 — Gemma4AudioFeatureExtractor (model Gemma4Config)
• gemma4_unified — Gemma4UnifiedAudioFeatureExtractor (model Gemma4UnifiedConfig)
• glmasr — WhisperFeatureExtractor (model GlmAsrConfig)
• gradium_phonon_tts — PocketTTSFeatureExtractor (model GradiumPhononTTSConfig)
• granite_speech — GraniteSpeechFeatureExtractor (model GraniteSpeechConfig)
• granite_speech5_ctc — GraniteSpeech5FeatureExtractor (model GraniteSpeech5CTCConfig)
• granite_speech5_encoder — GraniteSpeech5FeatureExtractor (model GraniteSpeech5EncoderConfig)
• granite_speech_plus — GraniteSpeechFeatureExtractor (model GraniteSpeechPlusConfig)
• higgs_audio_v2_tokenizer — DacFeatureExtractor (model HiggsAudioV2TokenizerConfig)
• hubert — Wav2Vec2FeatureExtractor (model HubertConfig)
• inkling_mm_model — InklingFeatureExtractor (model InklingConfig)
• kyutai_speech_to_text — KyutaiSpeechToTextFeatureExtractor (model KyutaiSpeechToTextConfig)
• lasr_ctc — LasrFeatureExtractor (model LasrCTCConfig)
• lasr_encoder — LasrFeatureExtractor (model LasrEncoderConfig)
• mimi — EncodecFeatureExtractor (model MimiConfig)
• moonshine — Wav2Vec2FeatureExtractor (model MoonshineConfig)
• moshi — EncodecFeatureExtractor (model MoshiConfig)
• moss_transcribe_diarize — MossTranscribeDiarizeFeatureExtractor (model MossTranscribeDiarizeConfig)
• muse_spark — MuseSparkFeatureExtractor (model MuseSparkConfig)
• musicgen — EncodecFeatureExtractor (model MusicgenConfig)
• musicgen_melody — MusicgenMelodyFeatureExtractor (model MusicgenMelodyConfig)
• nemo_speechlm — NemotronAsrStreamingFeatureExtractor (model Nemotron3_5TranscribeConfig)
• nemotron3_5_asr — NemotronAsrStreamingFeatureExtractor (model Nemotron3_5AsrConfig)
• nemotron3_diarization — NemotronAsrStreamingFeatureExtractor (model Nemotron3DiarizationConfig)
• nemotron_asr_streaming — NemotronAsrStreamingFeatureExtractor (model NemotronAsrStreamingConfig)
• nemotron_asr_streaming_encoder — NemotronAsrStreamingFeatureExtractor (model NemotronAsrStreamingEncoderConfig)
• neucodec — NeuCodecFeatureExtractor (model NeuCodecConfig)
• parakeet_ctc — ParakeetFeatureExtractor (model ParakeetCTCConfig)
• parakeet_encoder — ParakeetFeatureExtractor (model ParakeetEncoderConfig)
• parakeet_rnnt — ParakeetFeatureExtractor (model ParakeetRNNTConfig)
• parakeet_tdt — ParakeetFeatureExtractor (model ParakeetTDTConfig)
• pe_audio — PeAudioFeatureExtractor (model PeAudioConfig)
• pe_audio_video — PeAudioFeatureExtractor (model PeAudioVideoConfig)
• phi4_multimodal — Phi4MultimodalFeatureExtractor (model Phi4MultimodalConfig)
• pocket_tts — PocketTTSFeatureExtractor (model PocketTTSConfig)
• pocket_tts_audio_tokenizer — EncodecFeatureExtractor (model PocketTTSAudioTokenizerConfig)
• pop2piano — Pop2PianoFeatureExtractor (model Pop2PianoConfig)
• qwen2_5_omni — WhisperFeatureExtractor (model Qwen2_5OmniConfig)
• qwen2_audio — WhisperFeatureExtractor (model Qwen2AudioConfig)
• qwen3_asr — Qwen3ASRFeatureExtractor (model Qwen3ASRConfig)
• qwen3_omni_moe — WhisperFeatureExtractor (model Qwen3OmniMoeConfig)
• seamless_m4t — SeamlessM4TFeatureExtractor (model SeamlessM4TConfig)
• seamless_m4t_v2 — SeamlessM4TFeatureExtractor (model SeamlessM4Tv2Config)
• sew — Wav2Vec2FeatureExtractor (model SEWConfig)
• sew-d — Wav2Vec2FeatureExtractor (model SEWDConfig)
• speech_to_text — Speech2TextFeatureExtractor (model Speech2TextConfig)
• speecht5 — SpeechT5FeatureExtractor (model SpeechT5Config)
• unispeech — Wav2Vec2FeatureExtractor (model UniSpeechConfig)
• unispeech-sat — Wav2Vec2FeatureExtractor (model UniSpeechSatConfig)
• univnet — UnivNetFeatureExtractor (model UnivNetConfig)
• vibevoice — VibeVoiceAcousticTokenizerFeatureExtractor (model VibeVoiceConfig)
• vibevoice_acoustic_tokenizer — VibeVoiceAcousticTokenizerFeatureExtractor (model VibeVoiceAcousticTokenizerConfig)
• vibevoice_asr — VibeVoiceAcousticTokenizerFeatureExtractor (model VibeVoiceAsrConfig)
• voxtral — WhisperFeatureExtractor (model VoxtralConfig)
• voxtral_realtime — VoxtralRealtimeFeatureExtractor (model VoxtralRealtimeConfig)
• wav2vec2 — Wav2Vec2FeatureExtractor (model Wav2Vec2Config)
• wav2vec2-bert — Wav2Vec2FeatureExtractor (model Wav2Vec2BertConfig)
• wav2vec2-conformer — Wav2Vec2FeatureExtractor (model Wav2Vec2ConformerConfig)
• wavlm — Wav2Vec2FeatureExtractor (model WavLMConfig)
• whisper — WhisperFeatureExtractor (model WhisperConfig)
• xcodec — DacFeatureExtractor (model XcodecConfig)
• xcodec2 — Xcodec2FeatureExtractor (model Xcodec2Config)

Menyampaikan token=True diperlukan ketika Anda ingin menggunakan model privat.

>>> from transformers import AutoFeatureExtractor

>>> # Download feature extractor from huggingface.co and cache.
>>> feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/wav2vec2-base-960h")

>>> # If feature extractor files are in a directory (e.g. feature extractor was saved using *save_pretrained('./test/saved_model/')*)
>>> # feature_extractor = AutoFeatureExtractor.from_pretrained("./test/saved_model/")

Daftarkan fitur ekstraktor baru untuk kelas ini.

Instansiasi salah satu kelas pemroses gambar dari pustaka ini dari kosakata model terlatih sebelumnya.

Kelas image processor yang akan diinstansiasi dipilih berdasarkan properti model_type dari objek config (yang diberikan sebagai argumen atau dimuat dari pretrained_model_name_or_path jika memungkinkan), atau jika properti tersebut tidak ada, dengan menggunakan pattern matching pada pretrained_model_name_or_path:

• aimv2 — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (model Aimv2Config)
• aimv2_vision_model — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (model Aimv2VisionConfig)
• align — {'torchvision': 'EfficientNetImageProcessor', 'pil': 'EfficientNetImageProcessorPil'} (model AlignConfig)
• altclip — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (model AltCLIPConfig)
• aria — {'pil': 'AriaImageProcessorPil', 'torchvision': 'AriaImageProcessor'} (model AriaConfig)
• aya_vision — {'torchvision': 'GotOcr2ImageProcessor', 'pil': 'GotOcr2ImageProcessorPil'} (model AyaVisionConfig)
• beit — {'pil': 'BeitImageProcessorPil', 'torchvision': 'BeitImageProcessor'} (model BeitConfig)
• bit — {'pil': 'BitImageProcessorPil', 'torchvision': 'BitImageProcessor'} (model BitConfig)
• blip — {'pil': 'BlipImageProcessorPil', 'torchvision': 'BlipImageProcessor'} (model BlipConfig)
• blip-2 — {'torchvision': 'BlipImageProcessor', 'pil': 'BlipImageProcessorPil'} (model Blip2Config)
• bridgetower — {'pil': 'BridgeTowerImageProcessorPil', 'torchvision': 'BridgeTowerImageProcessor'} (model BridgeTowerConfig)
• chameleon — {'pil': 'ChameleonImageProcessorPil', 'torchvision': 'ChameleonImageProcessor'} (model ChameleonConfig)
• chinese_clip — {'pil': 'ChineseCLIPImageProcessorPil', 'torchvision': 'ChineseCLIPImageProcessor'} (model ChineseCLIPConfig)
• chmv2 — {'torchvision': 'CHMv2ImageProcessor'} (model CHMv2Config)
• clip — {'pil': 'CLIPImageProcessorPil', 'torchvision': 'CLIPImageProcessor'} (model CLIPConfig)
• clipseg — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (model CLIPSegConfig)
• cohere2_vision — {'torchvision': 'Cohere2VisionImageProcessor'} (model Cohere2VisionConfig)
• cohere_compass — {'pil': 'CohereCompassImageProcessorPil', 'torchvision': 'CohereCompassImageProcessor'} (model CohereCompassConfig)
• colpali — {'torchvision': 'SiglipImageProcessor', 'pil': 'SiglipImageProcessorPil'} (model ColPaliConfig)
• colqwen2 — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (model ColQwen2Config)
• conditional_detr — {'pil': 'ConditionalDetrImageProcessorPil', 'torchvision': 'ConditionalDetrImageProcessor'} (model ConditionalDetrConfig)
• convnext — {'pil': 'ConvNextImageProcessorPil', 'torchvision': 'ConvNextImageProcessor'} (model ConvNextConfig)
• convnextv2 — {'torchvision': 'ConvNextImageProcessor', 'pil': 'ConvNextImageProcessorPil'} (model ConvNextV2Config)
• cosmos3_edge — {'pil': 'Cosmos3EdgeImageProcessorPil', 'torchvision': 'Cosmos3EdgeImageProcessor'} (model Cosmos3EdgeConfig)
• cosmos3_omni — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (model Cosmos3OmniConfig)
• cvt — {'torchvision': 'ConvNextImageProcessor', 'pil': 'ConvNextImageProcessorPil'} (model CvtConfig)
• data2vec-vision — {'torchvision': 'BeitImageProcessor', 'pil': 'BeitImageProcessorPil'} (model Data2VecVisionConfig)
• deepseek_ocr2 — {'pil': 'DeepseekOcr2ImageProcessorPil', 'torchvision': 'DeepseekOcr2ImageProcessor'} (model DeepseekOcr2Config)
• deepseek_vl — {'pil': 'DeepseekVLImageProcessorPil', 'torchvision': 'DeepseekVLImageProcessor'} (model DeepseekVLConfig)
• deepseek_vl_hybrid — {'pil': 'DeepseekVLHybridImageProcessorPil', 'torchvision': 'DeepseekVLHybridImageProcessor'} (model DeepseekVLHybridConfig)
• deformable_detr — {'pil': 'DeformableDetrImageProcessorPil', 'torchvision': 'DeformableDetrImageProcessor'} (model DeformableDetrConfig)
• deimv2 — {'torchvision': 'RTDetrImageProcessor', 'pil': 'RTDetrImageProcessorPil'} (model Deimv2Config)
• deit — {'pil': 'DeiTImageProcessorPil', 'torchvision': 'DeiTImageProcessor'} (model DeiTConfig)
• depth_anything — {'torchvision': 'DPTImageProcessor', 'pil': 'DPTImageProcessorPil'} (model DepthAnythingConfig)
• depth_pro — {'torchvision': 'DepthProImageProcessor'} (model DepthProConfig)
• detr — {'pil': 'DetrImageProcessorPil', 'torchvision': 'DetrImageProcessor'} (model DetrConfig)
• dinat — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (model DinatConfig)
• dinov2 — {'torchvision': 'BitImageProcessor', 'pil': 'BitImageProcessorPil'} (model Dinov2Config)
• dinov3_vit — {'torchvision': 'DINOv3ViTImageProcessor'} (model DINOv3ViTConfig)
• donut-swin — {'torchvision': 'DonutImageProcessor', 'pil': 'DonutImageProcessorPil'} (model DonutSwinConfig)
• dpt — {'pil': 'DPTImageProcessorPil', 'torchvision': 'DPTImageProcessor'} (model DPTConfig)
• edgetam — {'torchvision': 'Sam2ImageProcessor'} (model EdgeTamConfig)
• efficientloftr — {'pil': 'EfficientLoFTRImageProcessorPil', 'torchvision': 'EfficientLoFTRImageProcessor'} (model EfficientLoFTRConfig)
• efficientnet — {'pil': 'EfficientNetImageProcessorPil', 'torchvision': 'EfficientNetImageProcessor'} (model EfficientNetConfig)
• embedding_gemma2 — {'pil': 'Gemma4ImageProcessorPil', 'torchvision': 'Gemma4ImageProcessor'} (model EmbeddingGemma2Config)
• emu3 — {'pil': 'Emu3ImageProcessor'} (model Emu3Config)
• eomt — {'pil': 'EomtImageProcessorPil', 'torchvision': 'EomtImageProcessor'} (model EomtConfig)
• eomt_dinov3 — {'torchvision': 'EomtImageProcessor', 'pil': 'EomtImageProcessorPil'} (model EomtDinov3Config)
• ernie4_5_vl_moe — {'pil': 'Ernie4_5_VLMoeImageProcessorPil', 'torchvision': 'Ernie4_5_VLMoeImageProcessor'} (model Ernie4_5_VLMoeConfig)
• exaone4_5 — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (model Exaone4_5_Config)
• flava — {'pil': 'FlavaImageProcessorPil', 'torchvision': 'FlavaImageProcessor'} (model FlavaConfig)
• florence2 — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (model Florence2Config)
• focalnet — {'torchvision': 'BitImageProcessor', 'pil': 'BitImageProcessorPil'} (model FocalNetConfig)
• fuyu — {'pil': 'FuyuImageProcessorPil', 'torchvision': 'FuyuImageProcessor'} (model FuyuConfig)
• gemma3 — {'pil': 'Gemma3ImageProcessorPil', 'torchvision': 'Gemma3ImageProcessor'} (model Gemma3Config)
• gemma3n — {'torchvision': 'SiglipImageProcessor', 'pil': 'SiglipImageProcessorPil'} (model Gemma3nConfig)
• gemma4 — {'pil': 'Gemma4ImageProcessorPil', 'torchvision': 'Gemma4ImageProcessor'} (model Gemma4Config)
• gemma4_unified — {'torchvision': 'Gemma4UnifiedImageProcessor'} (model Gemma4UnifiedConfig)
• git — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (model GitConfig)
• glm46v — {'pil': 'Glm46VImageProcessorPil', 'torchvision': 'Glm46VImageProcessor'} (model Glm46VConfig)
• glm4v — {'pil': 'Glm4vImageProcessorPil', 'torchvision': 'Glm4vImageProcessor'} (model Glm4vConfig)
• glm5_next — {'pil': 'Glm5NextImageProcessorPil', 'torchvision': 'Glm5NextImageProcessor'} (model Glm5NextConfig)
• glm_image — {'pil': 'GlmImageImageProcessorPil', 'torchvision': 'GlmImageImageProcessor'} (model GlmImageConfig)
• glmga — {'pil': 'GlmgaImageProcessorPil', 'torchvision': 'GlmgaImageProcessor'} (model GlmgaConfig)
• glpn — {'pil': 'GLPNImageProcessorPil', 'torchvision': 'GLPNImageProcessor'} (model GLPNConfig)
• got_ocr2 — {'pil': 'GotOcr2ImageProcessorPil', 'torchvision': 'GotOcr2ImageProcessor'} (model GotOcr2Config)
• granite4_vision — {'torchvision': 'LlavaNextImageProcessor', 'pil': 'LlavaNextImageProcessorPil'} (model Granite4VisionConfig)
• grounding-dino — {'pil': 'GroundingDinoImageProcessorPil', 'torchvision': 'GroundingDinoImageProcessor'} (model GroundingDinoConfig)
• groupvit — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (model GroupViTConfig)
• hiera — {'torchvision': 'BitImageProcessor', 'pil': 'BitImageProcessorPil'} (model HieraConfig)
• hunyuan_vl — {'pil': 'HunYuanVLImageProcessorPil', 'torchvision': 'HunYuanVLImageProcessor'} (model HunYuanVLConfig)
• hyperclovax_vision_v2 — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (model HyperCLOVAXVisionV2Config)
• idefics — {'pil': 'IdeficsImageProcessorPil', 'torchvision': 'IdeficsImageProcessor'} (model IdeficsConfig)
• idefics2 — {'pil': 'Idefics2ImageProcessorPil', 'torchvision': 'Idefics2ImageProcessor'} (model Idefics2Config)
• idefics3 — {'pil': 'Idefics3ImageProcessorPil', 'torchvision': 'Idefics3ImageProcessor'} (model Idefics3Config)
• ijepa — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (model IJepaConfig)
• imagegpt — {'pil': 'ImageGPTImageProcessorPil', 'torchvision': 'ImageGPTImageProcessor'} (model ImageGPTConfig)
• inkling_mm_model — {'torchvision': 'InklingImageProcessor'} (model InklingConfig)
• instructblip — {'torchvision': 'BlipImageProcessor', 'pil': 'BlipImageProcessorPil'} (model InstructBlipConfig)
• internvl — {'torchvision': 'GotOcr2ImageProcessor', 'pil': 'GotOcr2ImageProcessorPil'} (model InternVLConfig)
• janus — {'pil': 'JanusImageProcessorPil', 'torchvision': 'JanusImageProcessor'} (model JanusConfig)
• kimi_k25 — {'torchvision': 'Kimi_K25ImageProcessor'} (model Kimi_K25Config)
• kosmos-2 — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (model Kosmos2Config)
• kosmos-2.5 — {'torchvision': 'Kosmos2_5ImageProcessor', 'pil': 'Kosmos2_5ImageProcessorPil'} (model Kosmos2_5Config)
• layoutlmv2 — {'pil': 'LayoutLMv2ImageProcessorPil', 'torchvision': 'LayoutLMv2ImageProcessor'} (model LayoutLMv2Config)
• layoutlmv3 — {'pil': 'LayoutLMv3ImageProcessorPil', 'torchvision': 'LayoutLMv3ImageProcessor'} (model LayoutLMv3Config)
• layoutxlm — {'torchvision': 'LayoutLMv2ImageProcessor', 'pil': 'LayoutLMv2ImageProcessorPil'} (model LayoutXLMConfig)
• levit — {'pil': 'LevitImageProcessorPil', 'torchvision': 'LevitImageProcessor'} (model LevitConfig)
• lfm2_vl — {'torchvision': 'Lfm2VlImageProcessor'} (model Lfm2VlConfig)
• lightglue — {'pil': 'LightGlueImageProcessorPil', 'torchvision': 'LightGlueImageProcessor'} (model LightGlueConfig)
• lighton_ocr — {'torchvision': 'PixtralImageProcessor', 'pil': 'PixtralImageProcessorPil'} (model LightOnOcrConfig)
• llama4 — {'torchvision': 'Llama4ImageProcessor'} (model Llama4Config)
• llava — {'pil': 'LlavaImageProcessorPil', 'torchvision': 'LlavaImageProcessor'} (model LlavaConfig)
• llava_next — {'pil': 'LlavaNextImageProcessorPil', 'torchvision': 'LlavaNextImageProcessor'} (model LlavaNextConfig)
• llava_next_video — {'torchvision': 'LlavaNextImageProcessor', 'pil': 'LlavaNextImageProcessorPil'} (model LlavaNextVideoConfig)
• llava_onevision — {'pil': 'LlavaOnevisionImageProcessorPil', 'torchvision': 'LlavaOnevisionImageProcessor'} (model LlavaOnevisionConfig)
• lw_detr — {'torchvision': 'DeformableDetrImageProcessor', 'pil': 'DeformableDetrImageProcessorPil'} (model LwDetrConfig)
• mask2former — {'pil': 'Mask2FormerImageProcessorPil', 'torchvision': 'Mask2FormerImageProcessor'} (model Mask2FormerConfig)
• maskformer — {'pil': 'MaskFormerImageProcessorPil', 'torchvision': 'MaskFormerImageProcessor'} (model MaskFormerConfig)
• metaclip_2 — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (model MetaClip2Config)
• mgp-str — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (model MgpstrConfig)
• minicpm_ocr — {'torchvision': 'MiniCPMOcrImageProcessor'} (model MiniCPMOcrConfig)
• minicpmv4_6 — {'pil': 'MiniCPMV4_6ImageProcessorPil', 'torchvision': 'MiniCPMV4_6ImageProcessor'} (model MiniCPMV4_6Config)
• minicpmv4_7 — {'pil': 'MiniCPMV4_6ImageProcessorPil', 'torchvision': 'MiniCPMV4_6ImageProcessor'} (model MiniCPMV4_7Config)
• minimax_m3_vl — {'torchvision': 'MiniMaxM3VLImageProcessor'} (model MiniMaxM3VLConfig)
• mistral3 — {'torchvision': 'PixtralImageProcessor', 'pil': 'PixtralImageProcessorPil'} (model Mistral3Config)
• mistral_large4 — {'torchvision': 'PixtralImageProcessor', 'pil': 'PixtralImageProcessorPil'} (model MistralLarge4Config)
• mlcd — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (model MLCDVisionConfig)
• mllama — {'pil': 'MllamaImageProcessorPil', 'torchvision': 'MllamaImageProcessor'} (model MllamaConfig)
• mm-grounding-dino — {'torchvision': 'GroundingDinoImageProcessor', 'pil': 'GroundingDinoImageProcessorPil'} (model MMGroundingDinoConfig)
• mobilenet_v1 — {'pil': 'MobileNetV1ImageProcessorPil', 'torchvision': 'MobileNetV1ImageProcessor'} (model MobileNetV1Config)
• mobilenet_v2 — {'pil': 'MobileNetV2ImageProcessorPil', 'torchvision': 'MobileNetV2ImageProcessor'} (model MobileNetV2Config)
• mobilevit — {'pil': 'MobileViTImageProcessorPil', 'torchvision': 'MobileViTImageProcessor'} (model MobileViTConfig)
• mobilevitv2 — {'torchvision': 'MobileViTImageProcessor', 'pil': 'MobileViTImageProcessorPil'} (model MobileViTV2Config)
• molmo2 — {'torchvision': 'Molmo2ImageProcessor'} (model Molmo2Config)
• muse_glimmer — {'torchvision': 'MuseGlimmerImageProcessor'} (model MuseGlimmerConfig)
• muse_spark — {'torchvision': 'MuseGlimmerImageProcessor'} (model MuseSparkConfig)
• nemotron_h_omni — {'torchvision': 'NemotronH_Omni_Reasoning_V3ImageProcessor'} (model NemotronH_Omni_Reasoning_V3_Config)
• neomme — {'torchvision': 'NeoMMEImageProcessor'} (model NeoMMEConfig)
• nougat — {'pil': 'NougatImageProcessorPil', 'torchvision': 'NougatImageProcessor'} (model NougatConfig)
• omdet-turbo — {'torchvision': 'DetrImageProcessor', 'pil': 'DetrImageProcessorPil'} (model OmDetTurboConfig)
• oneformer — {'pil': 'OneFormerImageProcessorPil', 'torchvision': 'OneFormerImageProcessor'} (model OneFormerConfig)
• ovis2 — {'pil': 'Ovis2ImageProcessorPil', 'torchvision': 'Ovis2ImageProcessor'} (model Ovis2Config)
• owlv2 — {'pil': 'Owlv2ImageProcessorPil', 'torchvision': 'Owlv2ImageProcessor'} (model Owlv2Config)
• owlvit — {'pil': 'OwlViTImageProcessorPil', 'torchvision': 'OwlViTImageProcessor'} (model OwlViTConfig)
• paddleocr_vl — {'pil': 'PaddleOCRVLImageProcessorPil', 'torchvision': 'PaddleOCRVLImageProcessor'} (model PaddleOCRVLConfig)
• paligemma — {'torchvision': 'SiglipImageProcessor', 'pil': 'SiglipImageProcessorPil'} (model PaliGemmaConfig)
• perceiver — {'pil': 'PerceiverImageProcessorPil', 'torchvision': 'PerceiverImageProcessor'} (model PerceiverConfig)
• perception_lm — {'torchvision': 'PerceptionLMImageProcessor'} (model PerceptionLMConfig)
• phi4_multimodal — {'torchvision': 'Phi4MultimodalImageProcessor'} (model Phi4MultimodalConfig)
• pi0 — {'torchvision': 'PI0ImageProcessor'} (model PI0Config)
• pix2struct — {'pil': 'Pix2StructImageProcessorPil', 'torchvision': 'Pix2StructImageProcessor'} (model Pix2StructConfig)
• pixio — {'torchvision': 'BitImageProcessor', 'pil': 'BitImageProcessorPil'} (model PixioConfig)
• pixtral — {'pil': 'PixtralImageProcessorPil', 'torchvision': 'PixtralImageProcessor'} (model PixtralVisionConfig)
• poolformer — {'pil': 'PoolFormerImageProcessorPil', 'torchvision': 'PoolFormerImageProcessor'} (model PoolFormerConfig)
• pp_chart2table — {'pil': 'PPChart2TableImageProcessorPil', 'torchvision': 'PPChart2TableImageProcessor'} (model PPChart2TableConfig)
• pp_doclayout_v2 — {'torchvision': 'PPDocLayoutV2ImageProcessor'} (model PPDocLayoutV2Config)
• pp_doclayout_v3 — {'torchvision': 'PPDocLayoutV3ImageProcessor'} (model PPDocLayoutV3Config)
• pp_doclayout_v4 — {'torchvision': 'PPDocLayoutV4ImageProcessor'} (model PPDocLayoutV4Config)
• pp_formulanet — {'torchvision': 'PPFormulaNetImageProcessor'} (model PPFormulaNetConfig)
• pp_lcnet — {'torchvision': 'PPLCNetImageProcessor'} (model PPLCNetConfig)
• pp_ocrv5_mobile_det — {'torchvision': 'PPOCRV5ServerDetImageProcessor'} (model PPOCRV5MobileDetConfig)
• pp_ocrv5_mobile_rec — {'torchvision': 'PPOCRV5ServerRecImageProcessor'} (model PPOCRV5MobileRecConfig)
• pp_ocrv5_server_det — {'torchvision': 'PPOCRV5ServerDetImageProcessor'} (model PPOCRV5ServerDetConfig)
• pp_ocrv5_server_rec — {'torchvision': 'PPOCRV5ServerRecImageProcessor'} (model PPOCRV5ServerRecConfig)
• pp_ocrv6_medium_det — {'torchvision': 'PPOCRV5ServerDetImageProcessor'} (model PPOCRV6MediumDetConfig)
• pp_ocrv6_small_det — {'torchvision': 'PPOCRV5ServerDetImageProcessor'} (model PPOCRV6SmallDetConfig)
• pp_ocrv6_small_rec — {'torchvision': 'PPOCRV6SmallRecImageProcessor'} (model PPOCRV6SmallRecConfig)
• pp_ocrv6_tiny_rec — {'torchvision': 'PPOCRV6SmallRecImageProcessor'} (model PPOCRV6TinyRecConfig)
• prompt_depth_anything — {'pil': 'PromptDepthAnythingImageProcessorPil', 'torchvision': 'PromptDepthAnythingImageProcessor'} (model PromptDepthAnythingConfig)
• pvt — {'pil': 'PvtImageProcessorPil', 'torchvision': 'PvtImageProcessor'} (model PvtConfig)
• pvt_v2 — {'torchvision': 'PvtImageProcessor', 'pil': 'PvtImageProcessorPil'} (model PvtV2Config)
• qianfan_ocr — {'torchvision': 'GotOcr2ImageProcessor', 'pil': 'GotOcr2ImageProcessorPil'} (model QianfanOCRConfig)
• qwen2_5_omni — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (model Qwen2_5OmniConfig)
• qwen2_5_vl — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (model Qwen2_5_VLConfig)
• qwen2_vl — {'pil': 'Qwen2VLImageProcessorPil', 'torchvision': 'Qwen2VLImageProcessor'} (model Qwen2VLConfig)
• qwen3_5 — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (model Qwen3_5Config)
• qwen3_5_moe — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (model Qwen3_5MoeConfig)
• qwen3_omni_moe — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (model Qwen3OmniMoeConfig)
• qwen3_vl — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (model Qwen3VLConfig)
• qwen4_exp — {'torchvision': 'Qwen2VLImageProcessor', 'pil': 'Qwen2VLImageProcessorPil'} (model Qwen4ExpConfig)
• regnet — {'torchvision': 'ConvNextImageProcessor', 'pil': 'ConvNextImageProcessorPil'} (model RegNetConfig)
• resnet — {'torchvision': 'ConvNextImageProcessor', 'pil': 'ConvNextImageProcessorPil'} (model ResNetConfig)
• rf_detr — {'torchvision': 'RfDetrImageProcessor'} (model RfDetrConfig)
• rt_detr — {'pil': 'RTDetrImageProcessorPil', 'torchvision': 'RTDetrImageProcessor'} (model RTDetrConfig)
• sam — {'pil': 'SamImageProcessorPil', 'torchvision': 'SamImageProcessor'} (model SamConfig)
• sam2 — {'torchvision': 'Sam2ImageProcessor'} (model Sam2Config)
• sam2_video — {'torchvision': 'Sam2ImageProcessor'} (model Sam2VideoConfig)
• sam3 — {'torchvision': 'Sam3ImageProcessor'} (model Sam3Config)
• sam3_lite_text — {'torchvision': 'Sam3ImageProcessor'} (model Sam3LiteTextConfig)
• sam3_tracker — {'torchvision': 'Sam3ImageProcessor'} (model Sam3TrackerConfig)
• sam3_tracker_video — {'torchvision': 'Sam3ImageProcessor'} (model Sam3TrackerVideoConfig)
• sam3_video — {'torchvision': 'Sam3ImageProcessor'} (model Sam3VideoConfig)
• sam_hq — {'torchvision': 'SamImageProcessor', 'pil': 'SamImageProcessorPil'} (model SamHQConfig)
• sapiens2 — {'torchvision': 'Sapiens2ImageProcessor'} (model Sapiens2Config)
• segformer — {'pil': 'SegformerImageProcessorPil', 'torchvision': 'SegformerImageProcessor'} (model SegformerConfig)
• seggpt — {'pil': 'SegGptImageProcessorPil', 'torchvision': 'SegGptImageProcessor'} (model SegGptConfig)
• shieldgemma2 — {'torchvision': 'Gemma3ImageProcessor', 'pil': 'Gemma3ImageProcessorPil'} (model ShieldGemma2Config)
• siglip — {'pil': 'SiglipImageProcessorPil', 'torchvision': 'SiglipImageProcessor'} (model SiglipConfig)
• siglip2 — {'pil': 'Siglip2ImageProcessorPil', 'torchvision': 'Siglip2ImageProcessor'} (model Siglip2Config)
• slanet — {'torchvision': 'SLANeXtImageProcessor'} (model SLANetConfig)
• slanext — {'torchvision': 'SLANeXtImageProcessor'} (model SLANeXtConfig)
• smolvlm — {'pil': 'SmolVLMImageProcessorPil', 'torchvision': 'SmolVLMImageProcessor'} (model SmolVLMConfig)
• step3p7 — {'torchvision': 'Step3p7ImageProcessor'} (model Step3p7Config)
• superglue — {'pil': 'SuperGlueImageProcessorPil', 'torchvision': 'SuperGlueImageProcessor'} (model SuperGlueConfig)
• superpoint — {'pil': 'SuperPointImageProcessorPil', 'torchvision': 'SuperPointImageProcessor'} (model SuperPointConfig)
• swiftformer — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (model SwiftFormerConfig)
• swin — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (model SwinConfig)
• swin2sr — {'pil': 'Swin2SRImageProcessorPil', 'torchvision': 'Swin2SRImageProcessor'} (model Swin2SRConfig)
• swinv2 — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (model Swinv2Config)
• t5gemma2 — {'torchvision': 'Gemma3ImageProcessor', 'pil': 'Gemma3ImageProcessorPil'} (model T5Gemma2Config)
• t5gemma2_encoder — {'torchvision': 'Gemma3ImageProcessor', 'pil': 'Gemma3ImageProcessorPil'} (model T5Gemma2EncoderConfig)
• table-transformer — {'torchvision': 'DetrImageProcessor', 'pil': 'DetrImageProcessorPil'} (model TableTransformerConfig)
• textnet — {'pil': 'TextNetImageProcessorPil', 'torchvision': 'TextNetImageProcessor'} (model TextNetConfig)
• timesformer — {'pil': 'VideoMAEImageProcessorPil', 'torchvision': 'VideoMAEImageProcessor'} (model TimesformerConfig)
• timm_wrapper — {'pil': 'TimmWrapperImageProcessor'} (model TimmWrapperConfig)
• tipsv2 — {'torchvision': 'Tipsv2ImageProcessor'} (model Tipsv2Config)
• tipsv2_dpt — {'torchvision': 'Tipsv2DptImageProcessor'} (model Tipsv2DptConfig)
• trocr — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (model TrOCRConfig)
• tvp — {'pil': 'TvpImageProcessorPil', 'torchvision': 'TvpImageProcessor'} (model TvpConfig)
• udop — {'torchvision': 'LayoutLMv3ImageProcessor', 'pil': 'LayoutLMv3ImageProcessorPil'} (model UdopConfig)
• ultravbert — {'torchvision': 'UltraVBertImageProcessor'} (model UltraVBertConfig)
• unlimited_ocr — {'torchvision': 'UnlimitedOcrImageProcessor'} (model UnlimitedOcrConfig)
• upernet — {'torchvision': 'SegformerImageProcessor', 'pil': 'SegformerImageProcessorPil'} (model UperNetConfig)
• uvdoc — {'torchvision': 'UVDocImageProcessor'} (model UVDocConfig)
• video_llama_3 — {'pil': 'VideoLlama3ImageProcessorPil', 'torchvision': 'VideoLlama3ImageProcessor'} (model VideoLlama3Config)
• video_llava — {'pil': 'VideoLlavaImageProcessor'} (model VideoLlavaConfig)
• videomae — {'pil': 'VideoMAEImageProcessorPil', 'torchvision': 'VideoMAEImageProcessor'} (model VideoMAEConfig)
• vilt — {'pil': 'ViltImageProcessorPil', 'torchvision': 'ViltImageProcessor'} (model ViltConfig)
• vipllava — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (model VipLlavaConfig)
• vit — {'pil': 'ViTImageProcessorPil', 'torchvision': 'ViTImageProcessor'} (model ViTConfig)
• vit_mae — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (model ViTMAEConfig)
• vit_msn — {'torchvision': 'ViTImageProcessor', 'pil': 'ViTImageProcessorPil'} (model ViTMSNConfig)
• vitmatte — {'pil': 'VitMatteImageProcessorPil', 'torchvision': 'VitMatteImageProcessor'} (model VitMatteConfig)
• vitpose — {'pil': 'VitPoseImageProcessorPil', 'torchvision': 'VitPoseImageProcessor'} (model VitPoseConfig)
• vivit — {'torchvision': 'VivitImageProcessor'} (model VivitConfig)
• xclip — {'torchvision': 'CLIPImageProcessor', 'pil': 'CLIPImageProcessorPil'} (model XCLIPConfig)
• yolos — {'pil': 'YolosImageProcessorPil', 'torchvision': 'YolosImageProcessor'} (model YolosConfig)
• zoedepth — {'pil': 'ZoeDepthImageProcessorPil', 'torchvision': 'ZoeDepthImageProcessor'} (model ZoeDepthConfig)

Menyampaikan token=True diperlukan ketika Anda ingin menggunakan model privat.

>>> from transformers import AutoImageProcessor

>>> # Download image processor from huggingface.co and cache.
>>> image_processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224-in21k")

>>> # If image processor files are in a directory (e.g. image processor was saved using *save_pretrained('./test/saved_model/')*)
>>> # image_processor = AutoImageProcessor.from_pretrained("./test/saved_model/")

Daftarkan pemroses gambar baru untuk kelas ini.

Instansiasi salah satu kelas pemroses video dari pustaka ini dari kosakata model terlatih sebelumnya.

Kelas video processor yang akan diinstansiasi dipilih berdasarkan properti model_type dari objek config (yang diberikan sebagai argumen atau dimuat dari pretrained_model_name_or_path jika memungkinkan), atau jika properti tersebut tidak ada, dengan menggunakan pencocokan pola pada pretrained_model_name_or_path:

• cohere_compass — {'torchvision': 'CohereCompassVideoProcessor'} (model CohereCompassConfig)
• cosmos3_edge — {'torchvision': 'Cosmos3EdgeVideoProcessor'} (model Cosmos3EdgeConfig)
• cosmos3_omni — {'torchvision': 'Qwen3VLVideoProcessor'} (model Cosmos3OmniConfig)
• embedding_gemma2 — {'torchvision': 'EmbeddingGemma2VideoProcessor'} (model EmbeddingGemma2Config)
• ernie4_5_vl_moe — {'torchvision': 'Ernie4_5_VLMoeVideoProcessor'} (model Ernie4_5_VLMoeConfig)
• exaone4_5 — {'torchvision': 'Qwen2VLVideoProcessor'} (model Exaone4_5_Config)
• gemma4 — {'torchvision': 'Gemma4VideoProcessor'} (model Gemma4Config)
• gemma4_unified — {'torchvision': 'Gemma4UnifiedVideoProcessor'} (model Gemma4UnifiedConfig)
• glm46v — {'torchvision': 'Glm46VVideoProcessor'} (model Glm46VConfig)
• glm4v — {'torchvision': 'Glm4vVideoProcessor'} (model Glm4vConfig)
• glm5_next — {'torchvision': 'Glm5NextVideoProcessor'} (model Glm5NextConfig)
• glmga — {'torchvision': 'GlmgaVideoProcessor'} (model GlmgaConfig)
• hyperclovax_vision_v2 — {'torchvision': 'Qwen2VLVideoProcessor'} (model HyperCLOVAXVisionV2Config)
• instructblip — {'torchvision': 'InstructBlipVideoVideoProcessor'} (model InstructBlipConfig)
• instructblipvideo — {'torchvision': 'InstructBlipVideoVideoProcessor'} (model InstructBlipVideoConfig)
• internvl — {'torchvision': 'InternVLVideoProcessor'} (model InternVLConfig)
• kimi_k25 — {'torchvision': 'Kimi_K25VideoProcessor'} (model Kimi_K25Config)
• llava_next_video — {'torchvision': 'LlavaNextVideoVideoProcessor'} (model LlavaNextVideoConfig)
• llava_onevision — {'torchvision': 'LlavaOnevisionVideoProcessor'} (model LlavaOnevisionConfig)
• minicpm_ocr — {'torchvision': 'MiniCPMOcrVideoProcessor'} (model MiniCPMOcrConfig)
• minicpmv4_6 — {'torchvision': 'MiniCPMV4_6VideoProcessor'} (model MiniCPMV4_6Config)
• minicpmv4_7 — {'torchvision': 'MiniCPMV4_6VideoProcessor'} (model MiniCPMV4_7Config)
• minimax_m3_vl — {'torchvision': 'MiniMaxM3VLVideoProcessor'} (model MiniMaxM3VLConfig)
• molmo2 — {'torchvision': 'Molmo2VideoProcessor'} (model Molmo2Config)
• muse_glimmer — {'torchvision': 'MuseGlimmerVideoProcessor'} (model MuseGlimmerConfig)
• muse_spark — {'torchvision': 'MuseGlimmerVideoProcessor'} (model MuseSparkConfig)
• nemotron_h_omni — {'torchvision': 'NemotronH_Omni_Reasoning_V3VideoProcessor'} (model NemotronH_Omni_Reasoning_V3_Config)
• pe_audio_video — {'torchvision': 'PeVideoVideoProcessor'} (model PeAudioVideoConfig)
• pe_video — {'torchvision': 'PeVideoVideoProcessor'} (model PeVideoConfig)
• perception_lm — {'torchvision': 'PerceptionLMVideoProcessor'} (model PerceptionLMConfig)
• qwen2_5_omni — {'torchvision': 'Qwen2VLVideoProcessor'} (model Qwen2_5OmniConfig)
• qwen2_5_vl — {'torchvision': 'Qwen2VLVideoProcessor'} (model Qwen2_5_VLConfig)
• qwen2_vl — {'torchvision': 'Qwen2VLVideoProcessor'} (model Qwen2VLConfig)
• qwen3_5 — {'torchvision': 'Qwen3VLVideoProcessor'} (model Qwen3_5Config)
• qwen3_5_moe — {'torchvision': 'Qwen3VLVideoProcessor'} (model Qwen3_5MoeConfig)
• qwen3_omni_moe — {'torchvision': 'Qwen2VLVideoProcessor'} (model Qwen3OmniMoeConfig)
• qwen3_vl — {'torchvision': 'Qwen3VLVideoProcessor'} (model Qwen3VLConfig)
• qwen3_vl_moe — {'torchvision': 'Qwen3VLVideoProcessor'} (model Qwen3VLMoeConfig)
• qwen4_exp — {'torchvision': 'Qwen3VLVideoProcessor'} (model Qwen4ExpConfig)
• sam2_video — {'torchvision': 'Sam2VideoVideoProcessor'} (model Sam2VideoConfig)
• smolvlm — {'torchvision': 'SmolVLMVideoProcessor'} (model SmolVLMConfig)
• timesformer — {'torchvision': 'TimesformerVideoProcessor'} (model TimesformerConfig)
• video_llama_3 — {'torchvision': 'VideoLlama3VideoProcessor'} (model VideoLlama3Config)
• video_llava — {'torchvision': 'VideoLlavaVideoProcessor'} (model VideoLlavaConfig)
• videomae — {'torchvision': 'VideoMAEVideoProcessor'} (model VideoMAEConfig)
• videomt — {'torchvision': 'VideomtVideoProcessor'} (model VideomtConfig)
• videoprism — {'torchvision': 'LlavaOnevisionVideoProcessor'} (model VideoPrismConfig)
• vivit — {'torchvision': 'VivitVideoProcessor'} (model VivitConfig)
• vjepa2 — {'torchvision': 'VJEPA2VideoProcessor'} (model VJEPA2Config)

Menyampaikan token=True diperlukan ketika Anda ingin menggunakan model privat.

>>> from transformers import AutoVideoProcessor

>>> # Download video processor from huggingface.co and cache.
>>> video_processor = AutoVideoProcessor.from_pretrained("llava-hf/llava-onevision-qwen2-0.5b-ov-hf")

>>> # If video processor files are in a directory (e.g. video processor was saved using *save_pretrained('./test/saved_model/')*)
>>> # video_processor = AutoVideoProcessor.from_pretrained("./test/saved_model/")

Daftarkan pemroses video baru untuk kelas ini.

Instansiasi salah satu kelas pemroses dari pustaka ini dari kosakata model pralatih.

Kelas prosesor yang akan diinstansiasi dipilih berdasarkan properti model_type dari objek config (baik yang dilewatkan sebagai argumen maupun dimuat dari pretrained_model_name_or_path jika memungkinkan):

• aimv2 — CLIPProcessor (model Aimv2Config)
• align — AlignProcessor (model AlignConfig)
• altclip — AltCLIPProcessor (model AltCLIPConfig)
• aria — AriaProcessor (model AriaConfig)
• audioflamingo3 — AudioFlamingo3Processor (model AudioFlamingo3Config)
• aya_vision — AyaVisionProcessor (model AyaVisionConfig)
• bark — BarkProcessor (model BarkConfig)
• blip — BlipProcessor (model BlipConfig)
• blip-2 — Blip2Processor (model Blip2Config)
• bridgetower — BridgeTowerProcessor (model BridgeTowerConfig)
• bros — BrosProcessor (model BrosConfig)
• canary — CanaryProcessor (model CanaryConfig)
• chameleon — ChameleonProcessor (model ChameleonConfig)
• chinese_clip — ChineseCLIPProcessor (model ChineseCLIPConfig)
• clap — ClapProcessor (model ClapConfig)
• clip — CLIPProcessor (model CLIPConfig)
• clipseg — CLIPSegProcessor (model CLIPSegConfig)
• clvp — ClvpProcessor (model ClvpConfig)
• cohere2_vision — Cohere2VisionProcessor (model Cohere2VisionConfig)
• cohere_asr — CohereAsrProcessor (model CohereAsrConfig)
• cohere_compass — CohereCompassProcessor (model CohereCompassConfig)
• colmodernvbert — ColModernVBertProcessor (model ColModernVBertConfig)
• colpali — ColPaliProcessor (model ColPaliConfig)
• colqwen2 — ColQwen2Processor (model ColQwen2Config)
• cosmos3_edge — Cosmos3EdgeProcessor (model Cosmos3EdgeConfig)
• csm — CsmProcessor (model CsmConfig)
• deepseek_ocr2 — DeepseekOcr2Processor (model DeepseekOcr2Config)
• deepseek_vl — DeepseekVLProcessor (model DeepseekVLConfig)
• deepseek_vl_hybrid — DeepseekVLHybridProcessor (model DeepseekVLHybridConfig)
• dia — DiaProcessor (model DiaConfig)
• diffusion_gemma — Gemma4Processor (model DiffusionGemmaConfig)
• edgetam — Sam2Processor (model EdgeTamConfig)
• embedding_gemma2 — EmbeddingGemma2Processor (model EmbeddingGemma2Config)
• emu3 — Emu3Processor (model Emu3Config)
• ernie4_5_vl_moe — Ernie4_5_VLMoeProcessor (model Ernie4_5_VLMoeConfig)
• evolla — EvollaProcessor (model EvollaConfig)
• exaone4_5 — Exaone4_5_Processor (model Exaone4_5_Config)
• flava — FlavaProcessor (model FlavaConfig)
• florence2 — Florence2Processor (model Florence2Config)
• fun_asr_nano — FunAsrNanoProcessor (model FunAsrNanoConfig)
• fuyu — FuyuProcessor (model FuyuConfig)
• gemma3 — Gemma3Processor (model Gemma3Config)
• gemma3n — Gemma3nProcessor (model Gemma3nConfig)
• gemma4 — Gemma4Processor (model Gemma4Config)
• gemma4_unified — Gemma4UnifiedProcessor (model Gemma4UnifiedConfig)
• git — GitProcessor (model GitConfig)
• glm46v — Glm46VProcessor (model Glm46VConfig)
• glm4v — Glm4vProcessor (model Glm4vConfig)
• glm4v_moe — Glm4vProcessor (model Glm4vMoeConfig)
• glm5_next — Glm5NextProcessor (model Glm5NextConfig)
• glm_image — GlmImageProcessor (model GlmImageConfig)
• glmasr — GlmAsrProcessor (model GlmAsrConfig)
• got_ocr2 — GotOcr2Processor (model GotOcr2Config)
• gradium_phonon_tts — PocketTTSProcessor (model GradiumPhononTTSConfig)
• granite4_vision — Granite4VisionProcessor (model Granite4VisionConfig)
• granite_speech — GraniteSpeechProcessor (model GraniteSpeechConfig)
• granite_speech5_ctc — GraniteSpeech5Processor (model GraniteSpeech5CTCConfig)
• granite_speech_plus — GraniteSpeechProcessor (model GraniteSpeechPlusConfig)
• grounding-dino — GroundingDinoProcessor (model GroundingDinoConfig)
• groupvit — CLIPProcessor (model GroupViTConfig)
• higgs_audio_v2 — HiggsAudioV2Processor (model HiggsAudioV2Config)
• hubert — Wav2Vec2Processor (model HubertConfig)
• hunyuan_vl — HunYuanVLProcessor (model HunYuanVLConfig)
• hyperclovax_vision_v2 — HyperCLOVAXVisionV2Processor (model HyperCLOVAXVisionV2Config)
• idefics — IdeficsProcessor (model IdeficsConfig)
• idefics2 — Idefics2Processor (model Idefics2Config)
• idefics3 — Idefics3Processor (model Idefics3Config)
• inkling_mm_model — InklingProcessor (model InklingConfig)
• instructblip — InstructBlipProcessor (model InstructBlipConfig)
• instructblipvideo — InstructBlipVideoProcessor (model InstructBlipVideoConfig)
• internvl — InternVLProcessor (model InternVLConfig)
• janus — JanusProcessor (model JanusConfig)
• kimi_k25 — Kimi_K25Processor (model Kimi_K25Config)
• kyutai_speech_to_text — KyutaiSpeechToTextProcessor (model KyutaiSpeechToTextConfig)
• lasr_ctc — LasrProcessor (model LasrCTCConfig)
• lasr_encoder — LasrProcessor (model LasrEncoderConfig)
• layoutlmv2 — LayoutLMv2Processor (model LayoutLMv2Config)
• layoutlmv3 — LayoutLMv3Processor (model LayoutLMv3Config)
• layoutxlm — LayoutXLMProcessor (model LayoutXLMConfig)
• lfm2_vl — Lfm2VlProcessor (model Lfm2VlConfig)
• lighton_ocr — LightOnOcrProcessor (model LightOnOcrConfig)
• llama4 — Llama4Processor (model Llama4Config)
• llava — LlavaProcessor (model LlavaConfig)
• llava_next — LlavaNextProcessor (model LlavaNextConfig)
• llava_next_video — LlavaNextVideoProcessor (model LlavaNextVideoConfig)
• llava_onevision — LlavaOnevisionProcessor (model LlavaOnevisionConfig)
• markuplm — MarkupLMProcessor (model MarkupLMConfig)
• metaclip_2 — CLIPProcessor (model MetaClip2Config)
• mgp-str — MgpstrProcessor (model MgpstrConfig)
• minicpm_ocr — MiniCPMOcrProcessor (model MiniCPMOcrConfig)
• minicpmv4_6 — MiniCPMV4_6Processor (model MiniCPMV4_6Config)
• minicpmv4_7 — MiniCPMV4_7Processor (model MiniCPMV4_7Config)
• minimax_m3_vl — MiniMaxM3VLProcessor (model MiniMaxM3VLConfig)
• mistral3 — PixtralProcessor (model Mistral3Config)
• mistral_large4 — PixtralProcessor (model MistralLarge4Config)
• mllama — MllamaProcessor (model MllamaConfig)
• mm-grounding-dino — GroundingDinoProcessor (model MMGroundingDinoConfig)
• modernvbert — Idefics3Processor (model ModernVBertConfig)
• molmo2 — Molmo2Processor (model Molmo2Config)
• moonshine — Wav2Vec2Processor (model MoonshineConfig)
• moonshine_streaming — MoonshineStreamingProcessor (model MoonshineStreamingConfig)
• moss_transcribe_diarize — MossTranscribeDiarizeProcessor (model MossTranscribeDiarizeConfig)
• muse_glimmer — MuseGlimmerProcessor (model MuseGlimmerConfig)
• muse_spark — MuseSparkProcessor (model MuseSparkConfig)
• musicflamingo — MusicFlamingoProcessor (model MusicFlamingoConfig)
• musicgen — MusicgenProcessor (model MusicgenConfig)
• musicgen_melody — MusicgenMelodyProcessor (model MusicgenMelodyConfig)
• nemo_speechlm — Nemotron3_5TranscribeProcessor (model Nemotron3_5TranscribeConfig)
• nemotron3_5_asr — Nemotron3_5AsrProcessor (model Nemotron3_5AsrConfig)
• nemotron3_diarization — Nemotron3DiarizationProcessor (model Nemotron3DiarizationConfig)
• nemotron_asr_streaming — NemotronAsrStreamingProcessor (model NemotronAsrStreamingConfig)
• nemotron_h_omni — NemotronH_Omni_Reasoning_V3Processor (model NemotronH_Omni_Reasoning_V3_Config)
• neomme — NeoMMEProcessor (model NeoMMEConfig)
• nougat — NougatProcessor (model NougatConfig)
• omdet-turbo — OmDetTurboProcessor (model OmDetTurboConfig)
• oneformer — OneFormerProcessor (model OneFormerConfig)
• ovis2 — Ovis2Processor (model Ovis2Config)
• owlv2 — Owlv2Processor (model Owlv2Config)
• owlvit — OwlViTProcessor (model OwlViTConfig)
• paddleocr_vl — PaddleOCRVLProcessor (model PaddleOCRVLConfig)
• paligemma — PaliGemmaProcessor (model PaliGemmaConfig)
• parakeet_ctc — ParakeetProcessor (model ParakeetCTCConfig)
• parakeet_rnnt — ParakeetProcessor (model ParakeetRNNTConfig)
• parakeet_tdt — ParakeetProcessor (model ParakeetTDTConfig)
• pe_audio — PeAudioProcessor (model PeAudioConfig)
• pe_audio_video — PeAudioVideoProcessor (model PeAudioVideoConfig)
• pe_video — PeVideoProcessor (model PeVideoConfig)
• perception_lm — PerceptionLMProcessor (model PerceptionLMConfig)
• phi4_multimodal — Phi4MultimodalProcessor (model Phi4MultimodalConfig)
• pi0 — PI0Processor (model PI0Config)
• pix2struct — Pix2StructProcessor (model Pix2StructConfig)
• pixtral — PixtralProcessor (model PixtralVisionConfig)
• pocket_tts — PocketTTSProcessor (model PocketTTSConfig)
• pop2piano — Pop2PianoProcessor (model Pop2PianoConfig)
• pp_chart2table — PPChart2TableProcessor (model PPChart2TableConfig)
• pp_formulanet — PPFormulaNetProcessor (model PPFormulaNetConfig)
• qianfan_ocr — QianfanOCRProcessor (model QianfanOCRConfig)
• qwen2_5_omni — Qwen2_5OmniProcessor (model Qwen2_5OmniConfig)
• qwen2_5_vl — Qwen2_5_VLProcessor (model Qwen2_5_VLConfig)
• qwen2_audio — Qwen2AudioProcessor (model Qwen2AudioConfig)
• qwen2_vl — Qwen2VLProcessor (model Qwen2VLConfig)
• qwen3_5 — Qwen3VLProcessor (model Qwen3_5Config)
• qwen3_5_moe — Qwen3VLProcessor (model Qwen3_5MoeConfig)
• qwen3_asr — Qwen3ASRProcessor (model Qwen3ASRConfig)
• qwen3_omni_moe — Qwen3OmniMoeProcessor (model Qwen3OmniMoeConfig)
• qwen3_vl — Qwen3VLProcessor (model Qwen3VLConfig)
• qwen3_vl_moe — Qwen3VLProcessor (model Qwen3VLMoeConfig)
• qwen4_exp — Qwen3VLProcessor (model Qwen4ExpConfig)
• sam — SamProcessor (model SamConfig)
• sam2 — Sam2Processor (model Sam2Config)
• sam2_video — Sam2VideoProcessor (model Sam2VideoConfig)
• sam3 — Sam3Processor (model Sam3Config)
• sam3_lite_text — Sam3Processor (model Sam3LiteTextConfig)
• sam3_tracker — Sam3TrackerProcessor (model Sam3TrackerConfig)
• sam3_tracker_video — Sam3TrackerVideoProcessor (model Sam3TrackerVideoConfig)
• sam3_video — Sam3VideoProcessor (model Sam3VideoConfig)
• sam_hq — SamHQProcessor (model SamHQConfig)
• seamless_m4t — SeamlessM4TProcessor (model SeamlessM4TConfig)
• sew — Wav2Vec2Processor (model SEWConfig)
• sew-d — Wav2Vec2Processor (model SEWDConfig)
• siglip — SiglipProcessor (model SiglipConfig)
• siglip2 — Siglip2Processor (model Siglip2Config)
• smolvlm — SmolVLMProcessor (model SmolVLMConfig)
• speech_to_text — Speech2TextProcessor (model Speech2TextConfig)
• speecht5 — SpeechT5Processor (model SpeechT5Config)
• step3p7 — Step3p7Processor (model Step3p7Config)
• t5gemma2 — Gemma3Processor (model T5Gemma2Config)
• t5gemma2_encoder — Gemma3Processor (model T5Gemma2EncoderConfig)
• tipsv2 — Tipsv2Processor (model Tipsv2Config)
• trocr — TrOCRProcessor (model TrOCRConfig)
• tvp — TvpProcessor (model TvpConfig)
• udop — UdopProcessor (model UdopConfig)
• ultravbert — Idefics3Processor (model UltraVBertConfig)
• unispeech — Wav2Vec2Processor (model UniSpeechConfig)
• unispeech-sat — Wav2Vec2Processor (model UniSpeechSatConfig)
• unlimited_ocr — UnlimitedOcrProcessor (model UnlimitedOcrConfig)
• vibevoice — VibeVoiceProcessor (model VibeVoiceConfig)
• vibevoice_asr — VibeVoiceAsrProcessor (model VibeVoiceAsrConfig)
• video_llama_3 — VideoLlama3Processor (model VideoLlama3Config)
• video_llava — VideoLlavaProcessor (model VideoLlavaConfig)
• videoprism — VideoPrismProcessor (model VideoPrismConfig)
• vilt — ViltProcessor (model ViltConfig)
• vipllava — LlavaProcessor (model VipLlavaConfig)
• vision-text-dual-encoder — VisionTextDualEncoderProcessor (model VisionTextDualEncoderConfig)
• voxtral — VoxtralProcessor (model VoxtralConfig)
• voxtral_realtime — VoxtralRealtimeProcessor (model VoxtralRealtimeConfig)
• wav2vec2 — Wav2Vec2Processor (model Wav2Vec2Config)
• wav2vec2-bert — Wav2Vec2BertProcessor (model Wav2Vec2BertConfig)
• wav2vec2-conformer — Wav2Vec2Processor (model Wav2Vec2ConformerConfig)
• wavlm — Wav2Vec2Processor (model WavLMConfig)
• whisper — WhisperProcessor (model WhisperConfig)

Menyampaikan token=True diperlukan ketika Anda ingin menggunakan model privat.

>>> from transformers import AutoProcessor

>>> # Download processor from huggingface.co and cache.
>>> processor = AutoProcessor.from_pretrained("facebook/wav2vec2-base-960h")

>>> # If processor files are in a directory (e.g. processor was saved using *save_pretrained('./test/saved_model/')*)
>>> # processor = AutoProcessor.from_pretrained("./test/saved_model/")

Daftarkan prosesor baru untuk kelas ini.