xeon0618 commited on
Commit
edc6378
1 Parent(s): ba88db4

Upload 6 files

Browse files
config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
3
+ "activation_dropout": 0.1,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForCTC"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 256,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": false,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "sum",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": false,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "group",
53
+ "feat_proj_dropout": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.1,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_dropout_prob": 0.1,
60
+ "hidden_size": 768,
61
+ "initializer_range": 0.02,
62
+ "intermediate_size": 3072,
63
+ "layer_norm_eps": 1e-05,
64
+ "layerdrop": 0.1,
65
+ "mask_feature_length": 10,
66
+ "mask_feature_min_masks": 0,
67
+ "mask_feature_prob": 0.0,
68
+ "mask_time_length": 10,
69
+ "mask_time_min_masks": 2,
70
+ "mask_time_prob": 0.05,
71
+ "model_type": "wav2vec2",
72
+ "num_adapter_layers": 3,
73
+ "num_attention_heads": 12,
74
+ "num_codevector_groups": 2,
75
+ "num_codevectors_per_group": 320,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 12,
80
+ "num_negatives": 100,
81
+ "output_hidden_size": 768,
82
+ "pad_token_id": 0,
83
+ "proj_codevector_dim": 256,
84
+ "tdnn_dilation": [
85
+ 1,
86
+ 2,
87
+ 3,
88
+ 1,
89
+ 1
90
+ ],
91
+ "tdnn_dim": [
92
+ 512,
93
+ 512,
94
+ 512,
95
+ 512,
96
+ 1500
97
+ ],
98
+ "tdnn_kernel": [
99
+ 5,
100
+ 3,
101
+ 3,
102
+ 1,
103
+ 1
104
+ ],
105
+ "torch_dtype": "float32",
106
+ "transformers_version": "4.38.2",
107
+ "use_weighted_layer_sum": false,
108
+ "vocab_size": 87,
109
+ "xvector_output_dim": 512
110
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc3e9f72adb0cdf2be3034af640600b6d97d0ca9b3d4ee3c48704945240be72
3
+ size 377780252
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": false,
9
+ "sampling_rate": 16000
10
+ }
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 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "<pad>",
42
+ "processor_class": "Wav2Vec2Processor",
43
+ "replace_word_delimiter_char": " ",
44
+ "target_lang": null,
45
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
+ "unk_token": "<unk>",
47
+ "word_delimiter_token": "|"
48
+ }
vocab.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": 81,
3
+ "1": 74,
4
+ "2": 76,
5
+ "3": 78,
6
+ "4": 83,
7
+ "5": 75,
8
+ "6": 79,
9
+ "7": 80,
10
+ "8": 77,
11
+ "9": 82,
12
+ "</s>": 2,
13
+ "<pad>": 0,
14
+ "<s>": 1,
15
+ "<unk>": 3,
16
+ "|": 39,
17
+ "ँ": 40,
18
+ "ं": 8,
19
+ "ः": 47,
20
+ "अ": 72,
21
+ "आ": 65,
22
+ "इ": 31,
23
+ "ई": 19,
24
+ "उ": 25,
25
+ "ऊ": 67,
26
+ "ऋ": 38,
27
+ "ऍ": 11,
28
+ "ए": 49,
29
+ "ऐ": 14,
30
+ "ऑ": 59,
31
+ "ओ": 4,
32
+ "औ": 13,
33
+ "क": 28,
34
+ "ख": 24,
35
+ "ग": 27,
36
+ "घ": 15,
37
+ "ङ": 85,
38
+ "च": 52,
39
+ "छ": 7,
40
+ "ज": 9,
41
+ "झ": 66,
42
+ "ञ": 61,
43
+ "ट": 44,
44
+ "ठ": 18,
45
+ "ड": 10,
46
+ "ढ": 16,
47
+ "ण": 64,
48
+ "त": 45,
49
+ "थ": 56,
50
+ "द": 48,
51
+ "ध": 54,
52
+ "न": 63,
53
+ "प": 34,
54
+ "फ": 43,
55
+ "ब": 26,
56
+ "भ": 23,
57
+ "म": 55,
58
+ "य": 51,
59
+ "र": 29,
60
+ "ल": 22,
61
+ "व": 53,
62
+ "श": 71,
63
+ "ष": 50,
64
+ "स": 60,
65
+ "ह": 46,
66
+ "़": 37,
67
+ "ा": 57,
68
+ "ि": 20,
69
+ "ी": 6,
70
+ "ु": 69,
71
+ "ू": 30,
72
+ "ृ": 21,
73
+ "ॅ": 84,
74
+ "े": 42,
75
+ "ै": 17,
76
+ "ॉ": 36,
77
+ "ो": 12,
78
+ "ौ": 35,
79
+ "्": 68,
80
+ "क़": 33,
81
+ "ख़": 73,
82
+ "ग़": 41,
83
+ "ज़": 5,
84
+ "ड़": 58,
85
+ "ढ़": 62,
86
+ "फ़": 70,
87
+ "य़": 86,
88
+ "ॠ": 32
89
+ }