Hugging Face's logo

SLPL
/
Sharif-wav2vec2

Automatic Speech Recognition
Transformers
PyTorch
Persian
wav2vec2
audio
Eval Results
Inference Endpoints
Model card Files Community
5
sadrasabouri commited on
Commit
a6e6d0e
•
1 Parent(s): 258402a

del : not relevatns deleted.

Browse files
Files changed (3) hide show
  1. config.json +0 -115
  2. preprocessor_config.json +0 -9
  3. training_args.bin +0 -3
config.json DELETED
@@ -1,115 +0,0 @@
1
- {
2
- "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
3
- "activation_dropout": 0.1,
4
- "adapter_kernel_size": 3,
5
- "adapter_stride": 2,
6
- "add_adapter": false,
7
- "apply_spec_augment": true,
8
- "architectures": [
9
- "Wav2Vec2ForCTC"
10
- ],
11
- "attention_dropout": 0.05,
12
- "bos_token_id": 1,
13
- "classifier_proj_size": 256,
14
- "codevector_dim": 768,
15
- "contrastive_logits_temperature": 0.1,
16
- "conv_bias": true,
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": "mean",
45
- "ctc_zero_infinity": true,
46
- "diversity_loss_weight": 0.1,
47
- "do_stable_layer_norm": true,
48
- "eos_token_id": 2,
49
- "feat_extract_activation": "gelu",
50
- "feat_extract_dropout": 0.0,
51
- "feat_extract_norm": "layer",
52
- "feat_proj_dropout": 0.01249,
53
- "feat_quantizer_dropout": 0.0,
54
- "final_dropout": 0.0,
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": 0.01377,
62
- "mask_channel_length": 10,
63
- "mask_channel_min_space": 1,
64
- "mask_channel_other": 0.0,
65
- "mask_channel_prob": 0.0,
66
- "mask_channel_selection": "static",
67
- "mask_feature_length": 10,
68
- "mask_feature_min_masks": 0,
69
- "mask_feature_prob": 0,
70
- "mask_time_length": 10,
71
- "mask_time_min_masks": 2,
72
- "mask_time_min_space": 1,
73
- "mask_time_other": 0.0,
74
- "mask_time_prob": 0.05,
75
- "mask_time_selection": "static",
76
- "model_type": "wav2vec2",
77
- "num_adapter_layers": 3,
78
- "num_attention_heads": 16,
79
- "num_codevector_groups": 2,
80
- "num_codevectors_per_group": 320,
81
- "num_conv_pos_embedding_groups": 16,
82
- "num_conv_pos_embeddings": 128,
83
- "num_feat_extract_layers": 7,
84
- "num_hidden_layers": 24,
85
- "num_negatives": 100,
86
- "output_hidden_size": 1024,
87
- "pad_token_id": 0,
88
- "proj_codevector_dim": 768,
89
- "tdnn_dilation": [
90
- 1,
91
- 2,
92
- 3,
93
- 1,
94
- 1
95
- ],
96
- "tdnn_dim": [
97
- 512,
98
- 512,
99
- 512,
100
- 512,
101
- 1500
102
- ],
103
- "tdnn_kernel": [
104
- 5,
105
- 3,
106
- 3,
107
- 1,
108
- 1
109
- ],
110
- "torch_dtype": "float32",
111
- "transformers_version": "4.19.0.dev0",
112
- "use_weighted_layer_sum": false,
113
- "vocab_size": 40,
114
- "xvector_output_dim": 512
115
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
preprocessor_config.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "do_normalize": true,
3
- "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
- "feature_size": 1,
5
- "padding_side": "right",
6
- "padding_value": 0,
7
- "return_attention_mask": true,
8
- "sampling_rate": 16000
9
- }
 
 
 
 
 
 
 
 
 
 
training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b77249a77fb08e76d2b2022f945eddc9b9bced626b0b187d1e8d55a18d4d82ae
3
- size 3119