cdactvm commited on
Commit
f9b6a7c
1 Parent(s): b800a6c
alphabet.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"labels": ["<s>", "", "</s>", "⁇", " ", "ँ", "ं", "ः", "अ", "आ", "इ", "ई", "उ", "ऊ", "ॠ", "ऍ", "ऎ", "ए", "ऐ", "ऑ", "ओ", "औ", "क", "ख", "ग", "घ", "ङ", "च", "छ", "ज", "झ", "ञ", "ट", "ठ", "ड", "ढ", "ण", "त", "थ", "द", "ध", "न", "ऩ", "प", "फ", "ब", "भ", "म", "य", "र", "ऱ", "ल", "व", "श", "ष", "स", "ह", "़", "ा", "ि", "ी", "ु", "ू", "ृ", "े", "ै", "ॉ", "ॊ", "ो", "ौ", "्", "क़", "ख़", "ग़", "ज़", "ड़", "ढ़", "फ़"], "is_bpe": false}
config.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<s>",
12
+ "bos_token_id": 0,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "sum",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_lower_case": false,
48
+ "do_stable_layer_norm": false,
49
+ "eos_token": "</s>",
50
+ "eos_token_id": 2,
51
+ "feat_extract_activation": "gelu",
52
+ "feat_extract_norm": "group",
53
+ "feat_proj_dropout": 0.0,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.1,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 768,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 3072,
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.1,
63
+ "mask_feature_length": 10,
64
+ "mask_feature_min_masks": 0,
65
+ "mask_feature_prob": 0.0,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.05,
69
+ "model_type": "wav2vec2",
70
+ "num_adapter_layers": 3,
71
+ "num_attention_heads": 12,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
77
+ "num_hidden_layers": 12,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 768,
80
+ "pad_token": "[PAD]",
81
+ "pad_token_id": 1,
82
+ "proj_codevector_dim": 256,
83
+ "tdnn_dilation": [
84
+ 1,
85
+ 2,
86
+ 3,
87
+ 1,
88
+ 1
89
+ ],
90
+ "tdnn_dim": [
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 512,
95
+ 1500
96
+ ],
97
+ "tdnn_kernel": [
98
+ 5,
99
+ 3,
100
+ 3,
101
+ 1,
102
+ 1
103
+ ],
104
+ "torch_dtype": "float32",
105
+ "transformers_version": "4.20.1",
106
+ "unk_token": "[UNK]",
107
+ "use_weighted_layer_sum": false,
108
+ "vocab_size": 78,
109
+ "word_delimiter_token": "|",
110
+ "xvector_output_dim": 512
111
+ }
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": "Wav2Vec2ProcessorWithLM",
8
+ "return_attention_mask": false,
9
+ "sampling_rate": 16000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7851466db259e8c4006b4bc56477c85f3046607b3fa8bf4564588309c1b745d3
3
+ size 377795351
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 @@
 
 
1
+ {"<s>": 0, "<pad>": 1, "</s>": 2, "<unk>": 3, "|": 4, "ँ": 5, "ं": 6, "ः": 7, "अ": 8, "आ": 9, "इ": 10, "ई": 11, "उ": 12, "ऊ": 13, "ऋ": 14, "ऍ": 15, "ऎ": 16, "ए": 17, "ऐ": 18, "ऑ": 19, "ओ": 20, "औ": 21, "क": 22, "ख": 23, "ग": 24, "घ": 25, "ङ": 26, "च": 27, "छ": 28, "ज": 29, "झ": 30, "ञ": 31, "ट": 32, "ठ": 33, "ड": 34, "ढ": 35, "ण": 36, "त": 37, "थ": 38, "द": 39, "ध": 40, "न": 41, "ऩ": 42, "प": 43, "फ": 44, "ब": 45, "भ": 46, "म": 47, "य": 48, "र": 49, "ऱ": 50, "ल": 51, "व": 52, "श": 53, "ष": 54, "स": 55, "ह": 56, "़": 57, "ा": 58, "ि": 59, "ी": 60, "ु": 61, "ू": 62, "ृ": 63, "े": 64, "ै": 65, "ॉ": 66, "ॊ": 67, "ो": 68, "ौ": 69, "्": 70, "क़": 71, "ख़": 72, "ग़": 73, "ज़": 74, "ड़": 75, "ढ़": 76, "फ़": 77}