Xenova HF staff commited on
Commit
b30a09a
1 Parent(s): 27fdf29

Upload 6 files

Browse files
config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
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": 256,
14
+ "contrastive_logits_temperature": 0.1,
15
+ "conv_bias": false,
16
+ "conv_dim": [
17
+ 32,
18
+ 32,
19
+ 32
20
+ ],
21
+ "conv_kernel": [
22
+ 8,
23
+ 8,
24
+ 8
25
+ ],
26
+ "conv_stride": [
27
+ 4,
28
+ 4,
29
+ 4
30
+ ],
31
+ "ctc_loss_reduction": "sum",
32
+ "ctc_zero_infinity": false,
33
+ "diversity_loss_weight": 0.1,
34
+ "do_stable_layer_norm": false,
35
+ "eos_token_id": 2,
36
+ "feat_extract_activation": "gelu",
37
+ "feat_extract_dropout": 0.0,
38
+ "feat_extract_norm": "group",
39
+ "feat_proj_dropout": 0.0,
40
+ "feat_quantizer_dropout": 0.0,
41
+ "final_dropout": 0.1,
42
+ "hidden_act": "gelu",
43
+ "hidden_dropout": 0.1,
44
+ "hidden_dropout_prob": 0.1,
45
+ "hidden_size": 16,
46
+ "initializer_range": 0.02,
47
+ "intermediate_size": 20,
48
+ "layer_norm_eps": 1e-05,
49
+ "layerdrop": 0.1,
50
+ "mask_feature_length": 10,
51
+ "mask_feature_min_masks": 0,
52
+ "mask_feature_prob": 0.0,
53
+ "mask_time_length": 2,
54
+ "mask_time_min_masks": 2,
55
+ "mask_time_prob": 0.5,
56
+ "model_type": "wav2vec2",
57
+ "num_adapter_layers": 1,
58
+ "num_attention_heads": 2,
59
+ "num_codevector_groups": 2,
60
+ "num_codevectors_per_group": 320,
61
+ "num_conv_pos_embedding_groups": 2,
62
+ "num_conv_pos_embeddings": 16,
63
+ "num_feat_extract_layers": 3,
64
+ "num_hidden_layers": 4,
65
+ "num_negatives": 100,
66
+ "output_hidden_size": 16,
67
+ "pad_token_id": 0,
68
+ "proj_codevector_dim": 256,
69
+ "tdnn_dilation": [
70
+ 1,
71
+ 2
72
+ ],
73
+ "tdnn_dim": [
74
+ 32,
75
+ 32
76
+ ],
77
+ "tdnn_kernel": [
78
+ 5,
79
+ 3
80
+ ],
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.25.0.dev0",
83
+ "use_weighted_layer_sum": false,
84
+ "vocab_size": 32,
85
+ "xvector_output_dim": 32
86
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff991aad45bc8ab38bc139861ad6598a16344551f28aec63053bfaa1eb533349
3
+ size 217796
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
tokenizer.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<pad>",
9
+ "single_word": false,
10
+ "lstrip": true,
11
+ "rstrip": true,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<s>",
18
+ "single_word": false,
19
+ "lstrip": true,
20
+ "rstrip": true,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "</s>",
27
+ "single_word": false,
28
+ "lstrip": true,
29
+ "rstrip": true,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<unk>",
36
+ "single_word": false,
37
+ "lstrip": true,
38
+ "rstrip": true,
39
+ "normalized": false,
40
+ "special": true
41
+ }
42
+ ],
43
+ "normalizer": {
44
+ "type": "Replace",
45
+ "pattern": {
46
+ "String": " "
47
+ },
48
+ "content": "|"
49
+ },
50
+ "pre_tokenizer": {
51
+ "type": "Split",
52
+ "pattern": {
53
+ "Regex": ""
54
+ },
55
+ "behavior": "Isolated",
56
+ "invert": false
57
+ },
58
+ "post_processor": null,
59
+ "decoder": {
60
+ "type": "CTC",
61
+ "pad_token": "<pad>",
62
+ "word_delimiter_token": "|",
63
+ "cleanup": true
64
+ },
65
+ "model": {
66
+ "vocab": {
67
+ "<pad>": 0,
68
+ "<s>": 1,
69
+ "</s>": 2,
70
+ "<unk>": 3,
71
+ "|": 4,
72
+ "E": 5,
73
+ "T": 6,
74
+ "A": 7,
75
+ "O": 8,
76
+ "N": 9,
77
+ "I": 10,
78
+ "H": 11,
79
+ "S": 12,
80
+ "R": 13,
81
+ "D": 14,
82
+ "L": 15,
83
+ "U": 16,
84
+ "M": 17,
85
+ "W": 18,
86
+ "C": 19,
87
+ "F": 20,
88
+ "G": 21,
89
+ "Y": 22,
90
+ "P": 23,
91
+ "B": 24,
92
+ "V": 25,
93
+ "K": 26,
94
+ "'": 27,
95
+ "X": 28,
96
+ "J": 29,
97
+ "Q": 30,
98
+ "Z": 31
99
+ }
100
+ }
101
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "do_normalize": true,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 9223372036854775807,
7
+ "name_or_path": "facebook/wav2vec2-base-960h",
8
+ "pad_token": "<pad>",
9
+ "replace_word_delimiter_char": " ",
10
+ "return_attention_mask": false,
11
+ "special_tokens_map_file": "/home/huggingface/.cache/huggingface/hub/models--facebook--wav2vec2-base-960h/snapshots/22aad52d435eb6dbaf354bdad9b0da84ce7d6156/special_tokens_map.json",
12
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
13
+ "unk_token": "<unk>",
14
+ "word_delimiter_token": "|"
15
+ }
vocab.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 27,
3
+ "</s>": 2,
4
+ "<pad>": 0,
5
+ "<s>": 1,
6
+ "<unk>": 3,
7
+ "A": 7,
8
+ "B": 24,
9
+ "C": 19,
10
+ "D": 14,
11
+ "E": 5,
12
+ "F": 20,
13
+ "G": 21,
14
+ "H": 11,
15
+ "I": 10,
16
+ "J": 29,
17
+ "K": 26,
18
+ "L": 15,
19
+ "M": 17,
20
+ "N": 9,
21
+ "O": 8,
22
+ "P": 23,
23
+ "Q": 30,
24
+ "R": 13,
25
+ "S": 12,
26
+ "T": 6,
27
+ "U": 16,
28
+ "V": 25,
29
+ "W": 18,
30
+ "X": 28,
31
+ "Y": 22,
32
+ "Z": 31,
33
+ "|": 4
34
+ }