imvladikon commited on
Commit
8c65cf6
1 Parent(s): e55479e

Training in progress, step 400

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 108, "</s>": 109}
config.json CHANGED
@@ -1,6 +1,9 @@
1
  {
2
- "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
- "activation_dropout": 0.0,
 
 
 
4
  "apply_spec_augment": true,
5
  "architectures": [
6
  "Wav2Vec2ForCTC"
@@ -8,7 +11,7 @@
8
  "attention_dropout": 0.0,
9
  "bos_token_id": 1,
10
  "classifier_proj_size": 256,
11
- "codevector_dim": 768,
12
  "contrastive_logits_temperature": 0.1,
13
  "conv_bias": true,
14
  "conv_dim": [
@@ -49,31 +52,56 @@
49
  "feat_proj_dropout": 0.0,
50
  "feat_quantizer_dropout": 0.0,
51
  "final_dropout": 0.0,
52
- "gradient_checkpointing": false,
53
  "hidden_act": "gelu",
54
  "hidden_dropout": 0.0,
55
- "hidden_size": 1024,
56
  "initializer_range": 0.02,
57
- "intermediate_size": 4096,
58
  "layer_norm_eps": 1e-05,
59
  "layerdrop": 0.0,
60
- "mask_feature_length": 10,
61
- "mask_feature_prob": 0.0,
 
62
  "mask_time_length": 10,
63
- "mask_time_prob": 0.05,
 
64
  "model_type": "wav2vec2",
 
65
  "num_attention_heads": 16,
66
  "num_codevector_groups": 2,
67
  "num_codevectors_per_group": 320,
68
  "num_conv_pos_embedding_groups": 16,
69
  "num_conv_pos_embeddings": 128,
70
  "num_feat_extract_layers": 7,
71
- "num_hidden_layers": 24,
72
  "num_negatives": 100,
73
- "pad_token_id": 29,
74
- "proj_codevector_dim": 768,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
  "torch_dtype": "float32",
76
- "transformers_version": "4.11.3",
77
  "use_weighted_layer_sum": false,
78
- "vocab_size": 32
 
79
  }
 
1
  {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-1b",
3
+ "activation_dropout": 0.1,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
  "apply_spec_augment": true,
8
  "architectures": [
9
  "Wav2Vec2ForCTC"
 
11
  "attention_dropout": 0.0,
12
  "bos_token_id": 1,
13
  "classifier_proj_size": 256,
14
+ "codevector_dim": 1024,
15
  "contrastive_logits_temperature": 0.1,
16
  "conv_bias": true,
17
  "conv_dim": [
 
52
  "feat_proj_dropout": 0.0,
53
  "feat_quantizer_dropout": 0.0,
54
  "final_dropout": 0.0,
 
55
  "hidden_act": "gelu",
56
  "hidden_dropout": 0.0,
57
+ "hidden_size": 1280,
58
  "initializer_range": 0.02,
59
+ "intermediate_size": 5120,
60
  "layer_norm_eps": 1e-05,
61
  "layerdrop": 0.0,
62
+ "mask_feature_length": 64,
63
+ "mask_feature_min_masks": 0,
64
+ "mask_feature_prob": 0.25,
65
  "mask_time_length": 10,
66
+ "mask_time_min_masks": 2,
67
+ "mask_time_prob": 0.75,
68
  "model_type": "wav2vec2",
69
+ "num_adapter_layers": 3,
70
  "num_attention_heads": 16,
71
  "num_codevector_groups": 2,
72
  "num_codevectors_per_group": 320,
73
  "num_conv_pos_embedding_groups": 16,
74
  "num_conv_pos_embeddings": 128,
75
  "num_feat_extract_layers": 7,
76
+ "num_hidden_layers": 48,
77
  "num_negatives": 100,
78
+ "output_hidden_size": 1280,
79
+ "pad_token_id": 107,
80
+ "proj_codevector_dim": 1024,
81
+ "tdnn_dilation": [
82
+ 1,
83
+ 2,
84
+ 3,
85
+ 1,
86
+ 1
87
+ ],
88
+ "tdnn_dim": [
89
+ 512,
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 1500
94
+ ],
95
+ "tdnn_kernel": [
96
+ 5,
97
+ 3,
98
+ 3,
99
+ 1,
100
+ 1
101
+ ],
102
  "torch_dtype": "float32",
103
+ "transformers_version": "4.16.0.dev0",
104
  "use_weighted_layer_sum": false,
105
+ "vocab_size": 110,
106
+ "xvector_output_dim": 512
107
  }
preprocessor_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
  "feature_size": 1,
5
  "padding_side": "right",
6
- "padding_value": 0.0,
7
  "return_attention_mask": true,
8
  "sampling_rate": 16000
9
  }
 
3
  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
  "feature_size": 1,
5
  "padding_side": "right",
6
+ "padding_value": 0,
7
  "return_attention_mask": true,
8
  "sampling_rate": 16000
9
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc078e0fb4c130ae0ef06a0375134bb9f796f00e49f3754fed552c7e136f4b70
3
- size 1262054897
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64b32822466e070769a1da09a87aa88cdff1e2a2734026074c4f1c075fb5c0ce
3
+ size 3850876337
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./wav2vec2-xls-r-300m-hebrew", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0305e3ccd57fed2adb97e4ca093d51d130af8b98766d7002b5624399b091fde
3
- size 2863
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d28215427f7860a377b6d0316c2e0636f625fbe12b1de6f1fa34167c6667fc2
3
+ size 3055
vocab.json CHANGED
@@ -1 +1 @@
1
- {"\u05d0": 1, "\u05d1": 2, "\u05d2": 3, "\u05d3": 4, "\u05d4": 5, "\u05d5": 6, "\u05d6": 7, "\u05d7": 8, "\u05d8": 9, "\u05d9": 10, "\u05da": 11, "\u05db": 12, "\u05dc": 13, "\u05dd": 14, "\u05de": 15, "\u05df": 16, "\u05e0": 17, "\u05e1": 18, "\u05e2": 19, "\u05e3": 20, "\u05e4": 21, "\u05e5": 22, "\u05e6": 23, "\u05e7": 24, "\u05e8": 25, "\u05e9": 26, "\u05ea": 27, "|": 0, "[UNK]": 28, "[PAD]": 29}
 
1
+ {"!": 1, "\"": 2, "'": 3, ",": 4, "-": 5, ".": 6, "/": 7, "0": 8, "1": 9, "2": 10, "3": 11, "4": 12, "5": 13, "6": 14, "7": 15, "8": 16, "9": 17, "=": 18, "?": 19, "A": 20, "B": 21, "C": 22, "D": 23, "E": 24, "F": 25, "G": 26, "H": 27, "I": 28, "K": 29, "L": 30, "M": 31, "N": 32, "O": 33, "P": 34, "Q": 35, "R": 36, "S": 37, "T": 38, "V": 39, "W": 40, "X": 41, "Y": 42, "Z": 43, "[": 44, "_": 45, "a": 46, "b": 47, "c": 48, "d": 49, "e": 50, "f": 51, "g": 52, "h": 53, "i": 54, "k": 55, "l": 56, "m": 57, "n": 58, "o": 59, "p": 60, "q": 61, "r": 62, "s": 63, "t": 64, "u": 65, "v": 66, "w": 67, "x": 68, "y": 69, "z": 70, "ִ": 71, "ֶ": 72, "ָ": 73, "ֿ": 74, "ׁ": 75, "א": 76, "ב": 77, "ג": 78, "ד": 79, "ה": 80, "ו": 81, "ז": 82, "ח": 83, "ט": 84, "י": 85, "ך": 86, "כ": 87, "ל": 88, "ם": 89, "מ": 90, "ן": 91, "נ": 92, "ס": 93, "ע": 94, "ף": 95, "פ": 96, "ץ": 97, "צ": 98, "ק": 99, "ר": 100, "ש": 101, "ת": 102, "׳": 103, "״": 104, "–": 105, "|": 0, "[UNK]": 106, "[PAD]": 107}