Training in progress, step 400

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 126,
+  "<s>": 125,
+  "[PAD]": 124
+}

config.json

@@ -0,0 +1,116 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "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": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "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_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 124,
+  "proj_codevector_dim": 768,
+  "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": "4.38.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 127,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ba6faa409a06db941f28ba1fcdf5334297a7b6f1de04b405470193ce8f55f4a
+size 1262328180

preprocessor_config.json

@@ -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
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "123": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91ab2fec5e301146394b8549b631d79aa3256ed4f64b80996cfc77bd8fb702d2
+size 4728

vocab.json

@@ -0,0 +1,127 @@
+{
+  "!": 1,
+  "\"": 2,
+  "'": 3,
+  "(": 4,
+  ")": 5,
+  "*": 6,
+  "+": 7,
+  ",": 8,
+  "-": 9,
+  ".": 10,
+  "/": 11,
+  ":": 12,
+  ";": 13,
+  ">": 14,
+  "?": 15,
+  "@": 16,
+  "[": 17,
+  "[PAD]": 124,
+  "[UNK]": 123,
+  "]": 18,
+  "_": 19,
+  "`": 20,
+  "a": 21,
+  "b": 22,
+  "c": 23,
+  "d": 24,
+  "e": 25,
+  "f": 26,
+  "g": 27,
+  "h": 28,
+  "i": 29,
+  "j": 30,
+  "k": 31,
+  "l": 32,
+  "m": 33,
+  "n": 34,
+  "o": 35,
+  "p": 36,
+  "q": 37,
+  "r": 38,
+  "s": 39,
+  "t": 40,
+  "u": 41,
+  "v": 42,
+  "w": 43,
+  "x": 44,
+  "y": 45,
+  "z": 46,
+  "|": 0,
+  "~": 48,
+  "¡": 49,
+  "ª": 50,
+  "«": 51,
+  "°": 52,
+  "²": 53,
+  "´": 54,
+  "·": 55,
+  "»": 56,
+  "¿": 57,
+  "à": 58,
+  "á": 59,
+  "â": 60,
+  "ã": 61,
+  "ä": 62,
+  "å": 63,
+  "ç": 64,
+  "è": 65,
+  "é": 66,
+  "ë": 67,
+  "ì": 68,
+  "í": 69,
+  "î": 70,
+  "ï": 71,
+  "ð": 72,
+  "ñ": 73,
+  "ò": 74,
+  "ó": 75,
+  "ô": 76,
+  "ö": 77,
+  "ø": 78,
+  "ù": 79,
+  "ú": 80,
+  "ü": 81,
+  "ā": 82,
+  "ć": 83,
+  "č": 84,
+  "ė": 85,
+  "ı": 86,
+  "ł": 87,
+  "ň": 88,
+  "ō": 89,
+  "ŏ": 90,
+  "ő": 91,
+  "ř": 92,
+  "ś": 93,
+  "ş": 94,
+  "š": 95,
+  "ţ": 96,
+  "ū": 97,
+  "ž": 98,
+  "̀": 99,
+  "́": 100,
+  "̈": 101,
+  "̟": 102,
+  "̧": 103,
+  "β": 104,
+  "с": 105,
+  "ः": 106,
+  "ং": 107,
+  "ঃ": 108,
+  "ὑ": 109,
+  "‐": 110,
+  "–": 111,
+  "—": 112,
+  "―": 113,
+  "‘": 114,
+  "’": 115,
+  "“": 116,
+  "”": 117,
+  "•": 118,
+  "…": 119,
+  "ℂ": 120,
+  "ℕ": 121,
+  "ℤ": 122,
+  "�": 123
+}