model weights

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 122,
+  "<s>": 121
+}

config.json

@@ -0,0 +1,81 @@
+{
+  "activation_dropout": 0.0,
+  "adapter_act": "relu",
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": true,
+  "apply_spec_augment": false,
+  "architectures": [
+    "Wav2Vec2BertForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 121,
+  "classifier_proj_size": 768,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_depthwise_kernel_size": 31,
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": true,
+  "diversity_loss_weight": 0.1,
+  "dtype": "float32",
+  "eos_token_id": 122,
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.1,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "left_max_position_embeddings": 64,
+  "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_source_positions": 5000,
+  "model_type": "wav2vec2-bert",
+  "num_adapter_layers": 1,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 120,
+  "position_embeddings_type": "relative_key",
+  "proj_codevector_dim": 768,
+  "right_max_position_embeddings": 8,
+  "rotary_embedding_base": 10000,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "transformers_version": "4.57.6",
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 123,
+  "xvector_output_dim": 512
+}

final_metrics.json

@@ -0,0 +1,9 @@
+{
+  "loss": 0.4904663860797882,
+  "wer": 0.3875640020296139,
+  "cer": 0.18429939282676616,
+  "score": 0.28593169742819,
+  "runtime": 21.1894,
+  "samples_per_second": 37.755,
+  "steps_per_second": 3.162
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ea627314e14ea4bcb4937f727e290df212ce30e0fdfd0789db59231a4bf4c40
+size 2423323060

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 1,
+  "processor_class": "Wav2Vec2BertProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "119": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "122": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2BertProcessor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,123 @@
+{
+  "!": 0,
+  "\"": 1,
+  "&": 2,
+  "'": 3,
+  "(": 4,
+  ")": 5,
+  ",": 6,
+  "-": 7,
+  ".": 8,
+  "/": 9,
+  "0": 10,
+  "1": 11,
+  "2": 12,
+  "3": 13,
+  "4": 14,
+  "5": 15,
+  "6": 16,
+  "7": 17,
+  "8": 18,
+  "9": 19,
+  ":": 20,
+  ";": 21,
+  "<": 22,
+  "=": 23,
+  ">": 24,
+  "?": 25,
+  "A": 26,
+  "B": 27,
+  "C": 28,
+  "D": 29,
+  "E": 30,
+  "F": 31,
+  "G": 32,
+  "H": 33,
+  "I": 34,
+  "J": 35,
+  "K": 36,
+  "L": 37,
+  "M": 38,
+  "N": 39,
+  "O": 40,
+  "P": 41,
+  "Q": 42,
+  "R": 43,
+  "S": 44,
+  "T": 45,
+  "U": 46,
+  "V": 47,
+  "W": 48,
+  "X": 49,
+  "Y": 50,
+  "Z": 51,
+  "[PAD]": 120,
+  "[UNK]": 119,
+  "\\": 52,
+  "`": 53,
+  "a": 54,
+  "b": 55,
+  "c": 56,
+  "d": 57,
+  "e": 58,
+  "f": 59,
+  "g": 60,
+  "h": 61,
+  "i": 62,
+  "j": 63,
+  "k": 64,
+  "l": 65,
+  "m": 66,
+  "n": 67,
+  "o": 68,
+  "p": 69,
+  "q": 70,
+  "r": 71,
+  "s": 72,
+  "t": 73,
+  "u": 74,
+  "v": 75,
+  "w": 76,
+  "x": 77,
+  "y": 78,
+  "z": 79,
+  "|": 118,
+  "«": 80,
+  "»": 81,
+  "É": 82,
+  "×": 83,
+  "à": 84,
+  "á": 85,
+  "â": 86,
+  "ç": 87,
+  "è": 88,
+  "é": 89,
+  "ê": 90,
+  "ë": 91,
+  "ì": 92,
+  "í": 93,
+  "î": 94,
+  "ï": 95,
+  "ñ": 96,
+  "ò": 97,
+  "ó": 98,
+  "ô": 99,
+  "ù": 100,
+  "ú": 101,
+  "û": 102,
+  "ü": 103,
+  "þ": 104,
+  "ā": 105,
+  "ĝ": 106,
+  "Ķ": 107,
+  "ķ": 108,
+  "Ĺ": 109,
+  "ĺ": 110,
+  "Ŋ": 111,
+  "ŋ": 112,
+  "Œ": 113,
+  "œ": 114,
+  "ᵑ": 115,
+  "⭐": 116,
+  "️": 117
+}