Training in progress, step 400

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 85,
+  "<s>": 84
+}

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": 83,
+  "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": "4.47.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 86,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d93a00f0d9e6ae788ef50ff52f040318baa2ff62b969f097cec46308e25bde1
+size 1262160080

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 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "82": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "85": {
+      "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": "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 sha256:4a43b8b38960ceb694db402bdb1fd67934f33024d2aa1097f9289184615f4943
+size 5368

vocab.json

@@ -0,0 +1,86 @@
+{
+  "[PAD]": 83,
+  "[UNK]": 82,
+  "|": 0,
+  "ァ": 1,
+  "ア": 2,
+  "ィ": 3,
+  "イ": 4,
+  "ゥ": 5,
+  "ウ": 6,
+  "ェ": 7,
+  "エ": 8,
+  "ォ": 9,
+  "オ": 10,
+  "カ": 11,
+  "ガ": 12,
+  "キ": 13,
+  "ギ": 14,
+  "ク": 15,
+  "グ": 16,
+  "ケ": 17,
+  "ゲ": 18,
+  "コ": 19,
+  "ゴ": 20,
+  "サ": 21,
+  "ザ": 22,
+  "シ": 23,
+  "ジ": 24,
+  "ス": 25,
+  "ズ": 26,
+  "セ": 27,
+  "ゼ": 28,
+  "ソ": 29,
+  "ゾ": 30,
+  "タ": 31,
+  "ダ": 32,
+  "チ": 33,
+  "ッ": 34,
+  "ツ": 35,
+  "ヅ": 36,
+  "テ": 37,
+  "デ": 38,
+  "ト": 39,
+  "ド": 40,
+  "ナ": 41,
+  "ニ": 42,
+  "ヌ": 43,
+  "ネ": 44,
+  "ノ": 45,
+  "ハ": 46,
+  "バ": 47,
+  "パ": 48,
+  "ヒ": 49,
+  "ビ": 50,
+  "ピ": 51,
+  "フ": 52,
+  "ブ": 53,
+  "プ": 54,
+  "ヘ": 55,
+  "ベ": 56,
+  "ペ": 57,
+  "ホ": 58,
+  "ボ": 59,
+  "ポ": 60,
+  "マ": 61,
+  "ミ": 62,
+  "ム": 63,
+  "メ": 64,
+  "モ": 65,
+  "ャ": 66,
+  "ヤ": 67,
+  "ュ": 68,
+  "ユ": 69,
+  "ョ": 70,
+  "ヨ": 71,
+  "ラ": 72,
+  "リ": 73,
+  "ル": 74,
+  "レ": 75,
+  "ロ": 76,
+  "ワ": 77,
+  "ン": 78,
+  "ヴ": 79,
+  "・": 80,
+  "ー": 81
+}