gchhablani commited on
Commit
3ea1903
1 Parent(s): 503e04c
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
3
+ "activation_dropout": 0.0,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "Wav2Vec2ForCTC"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "conv_bias": true,
11
+ "conv_dim": [
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512
19
+ ],
20
+ "conv_kernel": [
21
+ 10,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 2,
27
+ 2
28
+ ],
29
+ "conv_stride": [
30
+ 5,
31
+ 2,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2
37
+ ],
38
+ "ctc_loss_reduction": "mean",
39
+ "ctc_zero_infinity": false,
40
+ "do_stable_layer_norm": true,
41
+ "eos_token_id": 2,
42
+ "feat_extract_activation": "gelu",
43
+ "feat_extract_dropout": 0.0,
44
+ "feat_extract_norm": "layer",
45
+ "feat_proj_dropout": 0.0,
46
+ "final_dropout": 0.0,
47
+ "gradient_checkpointing": true,
48
+ "hidden_act": "gelu",
49
+ "hidden_dropout": 0.1,
50
+ "hidden_size": 1024,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 4096,
53
+ "layer_norm_eps": 1e-05,
54
+ "layerdrop": 0.1,
55
+ "mask_channel_length": 10,
56
+ "mask_channel_min_space": 1,
57
+ "mask_channel_other": 0.0,
58
+ "mask_channel_prob": 0.0,
59
+ "mask_channel_selection": "static",
60
+ "mask_feature_length": 10,
61
+ "mask_feature_prob": 0.0,
62
+ "mask_time_length": 10,
63
+ "mask_time_min_space": 1,
64
+ "mask_time_other": 0.0,
65
+ "mask_time_prob": 0.05,
66
+ "mask_time_selection": "static",
67
+ "model_type": "wav2vec2",
68
+ "num_attention_heads": 16,
69
+ "num_conv_pos_embedding_groups": 16,
70
+ "num_conv_pos_embeddings": 128,
71
+ "num_feat_extract_layers": 7,
72
+ "num_hidden_layers": 24,
73
+ "pad_token_id": 79,
74
+ "transformers_version": "4.5.0.dev0",
75
+ "vocab_size": 80
76
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_size": 1,
4
+ "padding_side": "right",
5
+ "padding_value": 0.0,
6
+ "return_attention_mask": true,
7
+ "sampling_rate": 16000
8
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14d3e31303a48bced2db54cad006a078f9955ee42b9fabc7a9ca51da9e82d4ff
3
+ size 1262261847
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9cedeed8072ec2cf45c9812dafcd6855a08d7f57102501d8921dbe318e40fdc
3
+ size 2287
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"એ": 0, "ં": 1, "ઈ": 2, "ૈ": 3, "ી": 4, "ણ": 5, "હ": 6, "૦": 7, "ઓ": 8, "ૅ": 9, "ય": 10, "ત": 11, "ઍ": 12, "ષ": 13, "ઔ": 14, "ઠ": 15, "ઉ": 16, "છ": 17, "મ": 18, "આ": 19, "ન": 20, "઼": 21, "ક": 22, "લ": 23, "ો": 24, "૪": 25, "૨": 26, "૫": 27, "ડ": 28, "ફ": 29, "ઘ": 30, "૭": 31, "૮": 32, "ા": 33, "્": 34, "ઁ": 35, "ઐ": 36, "ઝ": 37, "ૃ": 38, "‍": 39, "ઢ": 40, "ઃ": 41, "વ": 42, "જ": 44, "પ": 45, "િ": 46, "ગ": 47, "થ": 48, "૯": 49, "ૌ": 50, "ઑ": 51, "ે": 52, "ૠ": 53, "ખ": 54, "ઇ": 55, "અ": 56, "ઋ": 57, "૩": 58, "ુ": 59, "બ": 60, "ળ": 61, "ૉ": 62, "૬": 63, "‌": 64, "દ": 65, "ૂ": 66, "ઊ": 67, "ૢ": 68, "સ": 69, "શ": 70, "૧": 71, "ચ": 72, "ધ": 73, "ર": 74, "ઞ": 75, "ટ": 76, "ભ": 77, "|": 43, "[UNK]": 78, "[PAD]": 79}