Hugging Face's logo

TanelAlumae
/
wav2vec2-large-xls-r-300m-openasr20-vn

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Inference Endpoints
Model card Files Community
Tanel Alumäe commited on
Commit
dccdc32
•
1 Parent(s): 0af0c91

Upload 6 files

Browse files
Files changed (6) hide show
  1. config.json +107 -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 +102 -0
config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_feature_length": 10,
63
+ "mask_feature_min_masks": 0,
64
+ "mask_feature_prob": 0.0,
65
+ "mask_time_length": 10,
66
+ "mask_time_min_masks": 2,
67
+ "mask_time_prob": 0.075,
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": 24,
77
+ "num_negatives": 100,
78
+ "output_hidden_size": 1024,
79
+ "pad_token_id": 0,
80
+ "proj_codevector_dim": 768,
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": "4.22.0.dev0",
104
+ "use_weighted_layer_sum": false,
105
+ "vocab_size": 100,
106
+ "xvector_output_dim": 512
107
+ }
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 sha256:311f4b13b33ccd295327ebf00c9cdc076a4fba216b873091741533d38bbb8687
3
+ size 1262302833
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 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "-": 99,
3
+ "</s>": 2,
4
+ "<pad>": 0,
5
+ "<s>": 1,
6
+ "<unk>": 3,
7
+ "_": 89,
8
+ "a": 12,
9
+ "b": 21,
10
+ "c": 8,
11
+ "d": 49,
12
+ "e": 36,
13
+ "f": 92,
14
+ "g": 10,
15
+ "h": 6,
16
+ "i": 7,
17
+ "j": 96,
18
+ "k": 25,
19
+ "l": 17,
20
+ "m": 11,
21
+ "n": 5,
22
+ "o": 18,
23
+ "p": 35,
24
+ "q": 53,
25
+ "r": 23,
26
+ "s": 38,
27
+ "t": 9,
28
+ "u": 15,
29
+ "v": 27,
30
+ "w": 95,
31
+ "x": 47,
32
+ "y": 16,
33
+ "z": 97,
34
+ "|": 4,
35
+ "à": 13,
36
+ "á": 22,
37
+ "â": 34,
38
+ "ã": 73,
39
+ "è": 77,
40
+ "é": 69,
41
+ "ê": 39,
42
+ "ì": 26,
43
+ "í": 62,
44
+ "ò": 64,
45
+ "ó": 19,
46
+ "ô": 20,
47
+ "õ": 90,
48
+ "ù": 72,
49
+ "ú": 59,
50
+ "ý": 80,
51
+ "ă": 48,
52
+ "đ": 14,
53
+ "ĩ": 82,
54
+ "ũ": 56,
55
+ "ơ": 44,
56
+ "ư": 24,
57
+ "ạ": 41,
58
+ "ả": 30,
59
+ "ấ": 31,
60
+ "ầ": 60,
61
+ "ẩ": 83,
62
+ "ẫ": 79,
63
+ "ậ": 50,
64
+ "ắ": 46,
65
+ "ằ": 66,
66
+ "ẳ": 85,
67
+ "ẵ": 94,
68
+ "ặ": 78,
69
+ "ẹ": 71,
70
+ "ẻ": 86,
71
+ "ẽ": 87,
72
+ "ế": 29,
73
+ "ề": 42,
74
+ "ể": 61,
75
+ "ễ": 84,
76
+ "ệ": 51,
77
+ "ỉ": 68,
78
+ "ị": 58,
79
+ "ọ": 52,
80
+ "ỏ": 65,
81
+ "ố": 45,
82
+ "ồ": 33,
83
+ "ổ": 67,
84
+ "ỗ": 74,
85
+ "ộ": 55,
86
+ "ớ": 37,
87
+ "ờ": 28,
88
+ "ở": 54,
89
+ "ỡ": 81,
90
+ "ợ": 43,
91
+ "ụ": 70,
92
+ "ủ": 63,
93
+ "ứ": 40,
94
+ "ừ": 32,
95
+ "ử": 75,
96
+ "ữ": 57,
97
+ "ự": 76,
98
+ "ỳ": 88,
99
+ "ỵ": 98,
100
+ "ỷ": 91,
101
+ "ỹ": 93
102
+ }