Training in progress, step 145

Browse files

Files changed (8) hide show

added_tokens.json +5 -0
config.json +116 -0
model.safetensors +3 -0
preprocessor_config.json +10 -0
special_tokens_map.json +30 -0
tokenizer_config.json +48 -0
training_args.bin +3 -0
vocab.json +114 -0

added_tokens.json ADDED Viewed

	@@ -0,0 +1,5 @@

+{
+  "</s>": 111,
+  "<s>": 110,
+  "[PAD]": 109
+}

config.json ADDED Viewed

	@@ -0,0 +1,116 @@

+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": 16,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "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": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "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": 109,
+  "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": "4.42.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 112,
+  "xvector_output_dim": 512
+}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3a334f6ab9df25edb6edd811f51fe1884633b21e2d6e58de067f3d2df6fe9a16
+size 1265726848

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
+}

special_tokens_map.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,48 @@

+{
+  "added_tokens_decoder": {
+    "108": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "111": {
+      "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": "eng",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:cfac583ba029e4ac1c6e9893bb27d7783570f06825843a6fe9247b7171a6564e
+size 5112

vocab.json ADDED Viewed

	@@ -0,0 +1,114 @@

+{
+  "eng": {
+    "!": 1,
+    "\"": 2,
+    "&": 3,
+    "'": 4,
+    ",": 5,
+    "-": 6,
+    ".": 7,
+    ":": 8,
+    "?": 9,
+    "[PAD]": 109,
+    "[UNK]": 108,
+    "a": 10,
+    "b": 11,
+    "c": 12,
+    "d": 13,
+    "e": 14,
+    "f": 15,
+    "g": 16,
+    "h": 17,
+    "i": 18,
+    "j": 19,
+    "k": 20,
+    "l": 21,
+    "m": 22,
+    "n": 23,
+    "o": 24,
+    "p": 25,
+    "q": 26,
+    "r": 27,
+    "s": 28,
+    "t": 29,
+    "u": 30,
+    "v": 31,
+    "w": 32,
+    "x": 33,
+    "y": 34,
+    "z": 35,
+    "|": 0,
+    "ँ": 37,
+    "ं": 38,
+    "ः": 39,
+    "अ": 40,
+    "आ": 41,
+    "इ": 42,
+    "ई": 43,
+    "उ": 44,
+    "ऊ": 45,
+    "ऋ": 46,
+    "ए": 47,
+    "ऐ": 48,
+    "ऑ": 49,
+    "ओ": 50,
+    "औ": 51,
+    "क": 52,
+    "ख": 53,
+    "ग": 54,
+    "घ": 55,
+    "च": 56,
+    "छ": 57,
+    "ज": 58,
+    "झ": 59,
+    "ञ": 60,
+    "ट": 61,
+    "ठ": 62,
+    "ड": 63,
+    "ढ": 64,
+    "ण": 65,
+    "त": 66,
+    "थ": 67,
+    "द": 68,
+    "ध": 69,
+    "न": 70,
+    "प": 71,
+    "फ": 72,
+    "ब": 73,
+    "भ": 74,
+    "म": 75,
+    "य": 76,
+    "र": 77,
+    "ल": 78,
+    "व": 79,
+    "श": 80,
+    "ष": 81,
+    "स": 82,
+    "ह": 83,
+    "़": 84,
+    "ा": 85,
+    "ि": 86,
+    "ी": 87,
+    "ु": 88,
+    "ू": 89,
+    "ृ": 90,
+    "ॅ": 91,
+    "े": 92,
+    "ै": 93,
+    "ॉ": 94,
+    "ो": 95,
+    "ौ": 96,
+    "्": 97,
+    "क़": 98,
+    "ग़": 99,
+    "ज़": 100,
+    "ड़": 101,
+    "ढ़": 102,
+    "फ़": 103,
+    "।": 104,
+    "‘": 105,
+    "’": 106,
+    "“": 107,
+    "”": 108
+  }
+}