Hugging Face's logo

karolnowakowski
/
wav2vec2-large-xlsr-53-ain-sakh

Automatic Speech Recognition
Transformers
PyTorch
Ainu (Japan)
wav2vec2
Inference Endpoints
Model card Files Community
1
karolnowakowski commited on
Commit
a77b1eb
•
1 Parent(s): bfb792f

Upload model files

Browse files
Files changed (6) hide show
  1. config.json +115 -0
  2. preprocessor_config.json +10 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +6 -0
  5. tokenizer_config.json +11 -0
  6. vocab.json +100 -0
config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "adapter_kernel_size": 3,
4
+ "adapter_stride": 2,
5
+ "add_adapter": false,
6
+ "apply_spec_augment": true,
7
+ "architectures": [
8
+ "Wav2Vec2ForCTC"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 1,
12
+ "classifier_proj_size": 256,
13
+ "codevector_dim": 768,
14
+ "contrastive_logits_temperature": 0.1,
15
+ "conv_bias": true,
16
+ "conv_dim": [
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512
24
+ ],
25
+ "conv_kernel": [
26
+ 10,
27
+ 3,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 2,
32
+ 2
33
+ ],
34
+ "conv_stride": [
35
+ 5,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2
42
+ ],
43
+ "ctc_loss_reduction": "sum",
44
+ "ctc_zero_infinity": false,
45
+ "diversity_loss_weight": 0.1,
46
+ "do_stable_layer_norm": true,
47
+ "eos_token_id": 2,
48
+ "feat_extract_activation": "gelu",
49
+ "feat_extract_dropout": 0.0,
50
+ "feat_extract_norm": "layer",
51
+ "feat_proj_dropout": 0.1,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "gradient_checkpointing": false,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 1024,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 4096,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.1,
62
+ "mask_channel_length": 10,
63
+ "mask_channel_min_space": 1,
64
+ "mask_channel_other": 0.0,
65
+ "mask_channel_prob": 0.0,
66
+ "mask_channel_selection": "static",
67
+ "mask_feature_length": 10,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.0,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_min_space": 1,
73
+ "mask_time_other": 0.0,
74
+ "mask_time_prob": 0.075,
75
+ "mask_time_selection": "static",
76
+ "model_type": "wav2vec2",
77
+ "num_adapter_layers": 3,
78
+ "num_attention_heads": 16,
79
+ "num_codevector_groups": 2,
80
+ "num_codevectors_per_group": 320,
81
+ "num_conv_pos_embedding_groups": 16,
82
+ "num_conv_pos_embeddings": 128,
83
+ "num_feat_extract_layers": 7,
84
+ "num_hidden_layers": 24,
85
+ "num_negatives": 100,
86
+ "output_hidden_size": 1024,
87
+ "pad_token_id": 0,
88
+ "proj_codevector_dim": 768,
89
+ "tdnn_dilation": [
90
+ 1,
91
+ 2,
92
+ 3,
93
+ 1,
94
+ 1
95
+ ],
96
+ "tdnn_dim": [
97
+ 512,
98
+ 512,
99
+ 512,
100
+ 512,
101
+ 1500
102
+ ],
103
+ "tdnn_kernel": [
104
+ 5,
105
+ 3,
106
+ 3,
107
+ 1,
108
+ 1
109
+ ],
110
+ "torch_dtype": "float32",
111
+ "transformers_version": "4.24.0",
112
+ "use_weighted_layer_sum": false,
113
+ "vocab_size": 98,
114
+ "xvector_output_dim": 512
115
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f629edf2dc9d41fadc243a6af763bd2d6d8f5a6eaf02d166caf475bda8bf907b
3
+ size 1262294641
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "pad_token": "<pad>",
6
+ "processor_class": "Wav2Vec2Processor",
7
+ "replace_word_delimiter_char": " ",
8
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
9
+ "unk_token": "<unk>",
10
+ "word_delimiter_token": "|"
11
+ }
vocab.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 10,
3
+ "</s>": 2,
4
+ "<pad>": 0,
5
+ "<s>": 1,
6
+ "<unk>": 3,
7
+ "a": 5,
8
+ "b": 96,
9
+ "c": 20,
10
+ "d": 91,
11
+ "e": 6,
12
+ "h": 11,
13
+ "i": 8,
14
+ "k": 9,
15
+ "m": 15,
16
+ "n": 7,
17
+ "o": 12,
18
+ "p": 19,
19
+ "r": 16,
20
+ "s": 18,
21
+ "t": 14,
22
+ "u": 13,
23
+ "w": 21,
24
+ "y": 17,
25
+ "|": 4,
26
+ "ア": 27,
27
+ "イ": 24,
28
+ "ウ": 25,
29
+ "エ": 61,
30
+ "オ": 51,
31
+ "カ": 32,
32
+ "ガ": 72,
33
+ "キ": 44,
34
+ "ギ": 90,
35
+ "ク": 47,
36
+ "グ": 95,
37
+ "ケ": 54,
38
+ "ゲ": 79,
39
+ "コ": 34,
40
+ "ゴ": 83,
41
+ "サ": 49,
42
+ "ザ": 93,
43
+ "シ": 30,
44
+ "ジ": 68,
45
+ "ス": 70,
46
+ "ズ": 78,
47
+ "セ": 87,
48
+ "ゼ": 89,
49
+ "ソ": 38,
50
+ "ゾ": 94,
51
+ "タ": 33,
52
+ "ダ": 26,
53
+ "チ": 37,
54
+ "ッ": 29,
55
+ "ツ": 59,
56
+ "ヅ": 80,
57
+ "テ": 31,
58
+ "デ": 46,
59
+ "ト": 35,
60
+ "ド": 60,
61
+ "ナ": 36,
62
+ "ニ": 50,
63
+ "ヌ": 86,
64
+ "ネ": 65,
65
+ "ノ": 23,
66
+ "ハ": 40,
67
+ "バ": 52,
68
+ "パ": 76,
69
+ "ヒ": 69,
70
+ "ビ": 88,
71
+ "ピ": 84,
72
+ "フ": 71,
73
+ "ブ": 67,
74
+ "プ": 92,
75
+ "ヘ": 85,
76
+ "ベ": 73,
77
+ "ホ": 64,
78
+ "ボ": 81,
79
+ "ポ": 97,
80
+ "マ": 39,
81
+ "ミ": 56,
82
+ "ム": 63,
83
+ "メ": 62,
84
+ "モ": 43,
85
+ "ャ": 53,
86
+ "ヤ": 45,
87
+ "ュ": 77,
88
+ "ユ": 66,
89
+ "ョ": 75,
90
+ "ヨ": 58,
91
+ "ラ": 42,
92
+ "リ": 55,
93
+ "ル": 41,
94
+ "レ": 48,
95
+ "ロ": 74,
96
+ "ワ": 57,
97
+ "ヲ": 82,
98
+ "ン": 22,
99
+ "ー": 28
100
+ }