Hugging Face's logo

deepdml
/
output

Automatic Speech Recognition Transformers PyTorch
Abkhaz wav2vec2 mozilla-foundation/common_voice_7_0 generated_from_trainer Inference Endpoints
Model card Files Community
deepdml commited on
Commit
508ad10
•
1 Parent(s): eddcf31

Training in progress, step 500

Browse files
Files changed (4) hide show
  1. config.json +40 -29
  2. preprocessor_config.json +2 -2
  3. pytorch_model.bin +2 -2
  4. training_args.bin +1 -1
config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "_name_or_path": "hf-test/xls-r-dummy",
3
- "activation_dropout": 0.0,
4
  "adapter_kernel_size": 3,
5
  "adapter_stride": 2,
6
  "add_adapter": false,
@@ -11,23 +11,35 @@
11
  "attention_dropout": 0.0,
12
  "bos_token_id": 1,
13
  "classifier_proj_size": 256,
14
- "codevector_dim": 256,
15
  "contrastive_logits_temperature": 0.1,
16
- "conv_bias": false,
17
  "conv_dim": [
18
- 32,
19
- 32,
20
- 32
 
 
 
 
21
  ],
22
  "conv_kernel": [
23
- 8,
24
- 8,
25
- 8
 
 
 
 
26
  ],
27
  "conv_stride": [
28
- 4,
29
- 4,
30
- 4
 
 
 
 
31
  ],
32
  "ctc_loss_reduction": "mean",
33
  "ctc_zero_infinity": false,
@@ -42,31 +54,30 @@
42
  "final_dropout": 0.0,
43
  "hidden_act": "gelu",
44
  "hidden_dropout": 0.0,
45
- "hidden_dropout_prob": 0.1,
46
- "hidden_size": 16,
47
  "initializer_range": 0.02,
48
- "intermediate_size": 20,
49
  "layer_norm_eps": 1e-05,
50
  "layerdrop": 0.0,
51
- "mask_feature_length": 10,
52
  "mask_feature_min_masks": 0,
53
- "mask_feature_prob": 0.0,
54
  "mask_time_length": 10,
55
  "mask_time_min_masks": 2,
56
- "mask_time_prob": 0.05,
57
  "model_type": "wav2vec2",
58
  "num_adapter_layers": 3,
59
- "num_attention_heads": 2,
60
  "num_codevector_groups": 2,
61
  "num_codevectors_per_group": 320,
62
- "num_conv_pos_embedding_groups": 2,
63
- "num_conv_pos_embeddings": 16,
64
- "num_feat_extract_layers": 3,
65
- "num_hidden_layers": 4,
66
- "num_negatives": 10,
67
- "output_hidden_size": 16,
68
- "pad_token_id": 50,
69
- "proj_codevector_dim": 256,
70
  "tdnn_dilation": [
71
  1,
72
  2,
@@ -91,6 +102,6 @@
91
  "torch_dtype": "float32",
92
  "transformers_version": "4.16.0.dev0",
93
  "use_weighted_layer_sum": false,
94
- "vocab_size": 53,
95
  "xvector_output_dim": 512
96
  }
1
  {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
+ "activation_dropout": 0.1,
4
  "adapter_kernel_size": 3,
5
  "adapter_stride": 2,
6
  "add_adapter": false,
11
  "attention_dropout": 0.0,
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": false,
54
  "final_dropout": 0.0,
55
  "hidden_act": "gelu",
56
  "hidden_dropout": 0.0,
57
+ "hidden_size": 1024,
 
58
  "initializer_range": 0.02,
59
+ "intermediate_size": 4096,
60
  "layer_norm_eps": 1e-05,
61
  "layerdrop": 0.0,
62
+ "mask_feature_length": 64,
63
  "mask_feature_min_masks": 0,
64
+ "mask_feature_prob": 0.25,
65
  "mask_time_length": 10,
66
  "mask_time_min_masks": 2,
67
+ "mask_time_prob": 0.75,
68
  "model_type": "wav2vec2",
69
  "num_adapter_layers": 3,
70
+ "num_attention_heads": 16,
71
  "num_codevector_groups": 2,
72
  "num_codevectors_per_group": 320,
73
+ "num_conv_pos_embedding_groups": 16,
74
+ "num_conv_pos_embeddings": 128,
75
+ "num_feat_extract_layers": 7,
76
+ "num_hidden_layers": 24,
77
+ "num_negatives": 100,
78
+ "output_hidden_size": 1024,
79
+ "pad_token_id": 34,
80
+ "proj_codevector_dim": 768,
81
  "tdnn_dilation": [
82
  1,
83
  2,
102
  "torch_dtype": "float32",
103
  "transformers_version": "4.16.0.dev0",
104
  "use_weighted_layer_sum": false,
105
+ "vocab_size": 37,
106
  "xvector_output_dim": 512
107
  }
preprocessor_config.json CHANGED
@@ -3,7 +3,7 @@
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
  }
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
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04505651c3f4e92e4686ab3cdf43761d0e71c4f42e830f26519a9f032ea215a4
3
- size 143910
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebbc8215078917fc0e0ea7429822effce638a1d40d779870fbcdfe70383d2823
3
+ size 1262075377
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d681b66505ad787d5d36692f16304513c3cbf4240a0d2204e0c0b2aed12d04bf
3
  size 2991
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cded0e41cfe89cf6ec4522d66b9f836aabcc80fa39561d4d07ff4ab1d55fb9c
3
  size 2991