speech_tokenizer/config.json

{
  "_name_or_path": "/workspace/audio_team/usr/jiayan/jiayan--TTS3--1.5B/pretrained_models/whisper-large-v3",
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "apply_spec_augment": false,
  "architectures": [
    "WhisperVQForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "begin_suppress_tokens": [
    220,
    50257
  ],
  "bos_token_id": 50257,
  "classifier_proj_size": 256,
  "d_model": 1280,
  "decoder_attention_heads": 20,
  "decoder_ffn_dim": 5120,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 32,
  "decoder_start_token_id": 50258,
  "dropout": 0.0,
  "encoder_attention_heads": 20,
  "encoder_causal_attention": false,
  "encoder_causal_convolution": false,
  "encoder_ffn_dim": 5120,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 32,
  "eos_token_id": 50257,
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "mask_feature_length": 10,
  "mask_feature_min_masks": 0,
  "mask_feature_prob": 0.0,
  "mask_time_length": 10,
  "mask_time_min_masks": 2,
  "mask_time_prob": 0.05,
  "max_length": 448,
  "max_source_positions": 1500,
  "max_target_positions": 448,
  "median_filter_width": 7,
  "model_type": "whisper",
  "num_hidden_layers": 32,
  "num_mel_bins": 128,
  "pad_token_id": 50256,
  "pitch_control": "fcpe_f0",
  "pitch_loss_scale": 2.0,
  "pitch_upsample_scale": 2,
  "pooling_kernel_size": 2,
  "pooling_position": 16,
  "pooling_type": "avg",
  "quantize_causal_block_size": 200,
  "quantize_causal_encoder": false,
  "quantize_commit_coefficient": 0.25,
  "quantize_ema_decay": 0.99,
  "quantize_encoder_only": false,
  "quantize_hidden_dim": null,
  "quantize_loss_scale": 10.0,
  "quantize_position": 16,
  "quantize_restart_interval": 100,
  "quantize_vocab_size": 32768,
  "scale_embedding": false,
  "skip_language_detection": true,
  "torch_dtype": "float32",
  "transformers_version": "4.44.1",
  "use_cache": true,
  "use_weighted_layer_sum": false,
  "vocab_size": 51866
}