upload weights

Browse files

Files changed (6) hide show

config.json +108 -0
preprocessor_config.json +10 -0
pytorch_model.bin +3 -0
special_tokens_map.json +6 -0
tokenizer_config.json +13 -0
vocab.json +156 -0

config.json ADDED Viewed

	@@ -0,0 +1,108 @@

+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-1b",
+  "activation_dropout": 0.05,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.05,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_attn_adapters": 1,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 1024,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 154,
+  "xvector_output_dim": 512
+}

preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5abcbd07e793c49e2d2bbba9ad1e9acf7b1e277089e35f4d13a414c46cc7c509
+size 3859750093

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,13 @@

+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json ADDED Viewed

	@@ -0,0 +1,156 @@

+{
+  "!": 75,
+  "\"": 62,
+  "$": 48,
+  "%": 47,
+  "&": 57,
+  "'": 31,
+  "+": 56,
+  ",": 44,
+  "-": 32,
+  ".": 37,
+  "/": 45,
+  "0": 27,
+  "1": 30,
+  "2": 35,
+  "3": 41,
+  "4": 39,
+  "5": 38,
+  "6": 40,
+  "7": 43,
+  "8": 42,
+  "9": 36,
+  ":": 46,
+  ";": 52,
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3,
+  "[": 59,
+  "]": 60,
+  "`": 92,
+  "a": 7,
+  "b": 24,
+  "c": 16,
+  "d": 15,
+  "e": 5,
+  "f": 19,
+  "g": 21,
+  "h": 13,
+  "i": 9,
+  "j": 29,
+  "k": 26,
+  "l": 14,
+  "m": 18,
+  "n": 10,
+  "o": 8,
+  "p": 20,
+  "q": 34,
+  "r": 12,
+  "s": 11,
+  "t": 6,
+  "u": 17,
+  "v": 25,
+  "w": 23,
+  "x": 28,
+  "y": 22,
+  "z": 33,
+  "|": 4,
+  "£": 68,
+  "¥": 53,
+  "§": 139,
+  "°": 58,
+  "²": 76,
+  "ß": 82,
+  "à": 84,
+  "á": 49,
+  "â": 81,
+  "ã": 66,
+  "ä": 78,
+  "å": 123,
+  "æ": 110,
+  "ç": 64,
+  "è": 79,
+  "é": 55,
+  "ê": 88,
+  "ë": 87,
+  "í": 50,
+  "î": 97,
+  "ï": 85,
+  "ð": 98,
+  "ñ": 83,
+  "ò": 105,
+  "ó": 67,
+  "ô": 86,
+  "õ": 69,
+  "ö": 74,
+  "ø": 91,
+  "ú": 70,
+  "û": 99,
+  "ü": 54,
+  "ý": 112,
+  "þ": 132,
+  "ā": 100,
+  "ă": 102,
+  "ć": 94,
+  "č": 89,
+  "ē": 143,
+  "ę": 119,
+  "ě": 140,
+  "ğ": 153,
+  "ī": 107,
+  "ı": 103,
+  "ł": 73,
+  "ń": 118,
+  "ň": 137,
+  "ō": 80,
+  "ő": 120,
+  "œ": 96,
+  "ř": 108,
+  "ş": 116,
+  "š": 90,
+  "ū": 101,
+  "ž": 95,
+  "ș": 104,
+  "ə": 138,
+  "ʻ": 115,
+  "́": 93,
+  "̇": 77,
+  "α": 106,
+  "κ": 109,
+  "π": 117,
+  "χ": 141,
+  "а": 144,
+  "в": 124,
+  "е": 125,
+  "з": 130,
+  "и": 113,
+  "й": 127,
+  "к": 114,
+  "л": 126,
+  "н": 128,
+  "ь": 131,
+  "я": 129,
+  "נ": 147,
+  "ע": 148,
+  "ṃ": 121,
+  "ạ": 111,
+  "ả": 145,
+  "ị": 146,
+  "ụ": 122,
+  "": 71,
+  "–": 61,
+  "—": 51,
+  "‘": 72,
+  "’": 65,
+  "”": 63,
+  "≡": 142,
+  "京": 149,
+  "先": 135,
+  "大": 151,
+  "尚": 134,
+  "时": 133,
+  "生": 136,
+  "都": 150,
+  "阪": 152
+}