Hugging Face's logo

roshna-omer
/
wav2vec2-large-xls-r-300m-ckb-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Inference Endpoints
Model card Files Metrics Community
roshna-omer commited on
Commit
18f59c0
•
1 Parent(s): df16c11

Training in progress, step 400

Browse files
Files changed (5) hide show
  1. config.json +109 -109
  2. model.safetensors +1 -1
  3. preprocessor_config.json +9 -9
  4. runs/Oct01_20-04-18_DESKTOP-F91JMJC/events.out.tfevents.1727802430.DESKTOP-F91JMJC.16788.0 +3 -0
  5. training_args.bin +1 -1
config.json CHANGED
@@ -1,109 +1,109 @@
1
- {
2
- "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
- "activation_dropout": 0.0,
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": 0.0,
13
- "bos_token_id": 1,
14
- "classifier_proj_size": 256,
15
- "codevector_dim": 768,
16
- "contrastive_logits_temperature": 0.1,
17
- "conv_bias": true,
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": "mean",
46
- "ctc_zero_infinity": false,
47
- "diversity_loss_weight": 0.1,
48
- "do_stable_layer_norm": true,
49
- "eos_token_id": 2,
50
- "feat_extract_activation": "gelu",
51
- "feat_extract_dropout": 0.0,
52
- "feat_extract_norm": "layer",
53
- "feat_proj_dropout": 0.0,
54
- "feat_quantizer_dropout": 0.0,
55
- "final_dropout": 0.0,
56
- "gradient_checkpointing": false,
57
- "hidden_act": "gelu",
58
- "hidden_dropout": 0.0,
59
- "hidden_size": 1024,
60
- "initializer_range": 0.02,
61
- "intermediate_size": 4096,
62
- "layer_norm_eps": 1e-05,
63
- "layerdrop": 0.0,
64
- "mask_feature_length": 10,
65
- "mask_feature_min_masks": 0,
66
- "mask_feature_prob": 0.0,
67
- "mask_time_length": 10,
68
- "mask_time_min_masks": 2,
69
- "mask_time_prob": 0.05,
70
- "model_type": "wav2vec2",
71
- "num_adapter_layers": 3,
72
- "num_attention_heads": 16,
73
- "num_codevector_groups": 2,
74
- "num_codevectors_per_group": 320,
75
- "num_conv_pos_embedding_groups": 16,
76
- "num_conv_pos_embeddings": 128,
77
- "num_feat_extract_layers": 7,
78
- "num_hidden_layers": 24,
79
- "num_negatives": 100,
80
- "output_hidden_size": 1024,
81
- "pad_token_id": 43,
82
- "proj_codevector_dim": 768,
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": "4.45.1",
106
- "use_weighted_layer_sum": false,
107
- "vocab_size": 46,
108
- "xvector_output_dim": 512
109
- }
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
+ "activation_dropout": 0.0,
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": 0.0,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 768,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
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": "mean",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.0,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.0,
59
+ "hidden_size": 1024,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 4096,
62
+ "layer_norm_eps": 1e-05,
63
+ "layerdrop": 0.0,
64
+ "mask_feature_length": 10,
65
+ "mask_feature_min_masks": 0,
66
+ "mask_feature_prob": 0.0,
67
+ "mask_time_length": 10,
68
+ "mask_time_min_masks": 2,
69
+ "mask_time_prob": 0.05,
70
+ "model_type": "wav2vec2",
71
+ "num_adapter_layers": 3,
72
+ "num_attention_heads": 16,
73
+ "num_codevector_groups": 2,
74
+ "num_codevectors_per_group": 320,
75
+ "num_conv_pos_embedding_groups": 16,
76
+ "num_conv_pos_embeddings": 128,
77
+ "num_feat_extract_layers": 7,
78
+ "num_hidden_layers": 24,
79
+ "num_negatives": 100,
80
+ "output_hidden_size": 1024,
81
+ "pad_token_id": 43,
82
+ "proj_codevector_dim": 768,
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": "4.45.1",
106
+ "use_weighted_layer_sum": false,
107
+ "vocab_size": 46,
108
+ "xvector_output_dim": 512
109
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecd92fddf2979f37d49e2d3022c4ed94e122c1c17a1aa54834ee363d3afc0978
3
  size 1261996080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80c9b66465ea38ba33e828378b36526dd649bfac568ddd7b67c324d8fa1d477e
3
  size 1261996080
preprocessor_config.json CHANGED
@@ -1,9 +1,9 @@
1
- {
2
- "do_normalize": true,
3
- "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
- "feature_size": 1,
5
- "padding_side": "right",
6
- "padding_value": 0.0,
7
- "return_attention_mask": true,
8
- "sampling_rate": 16000
9
- }
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
runs/Oct01_20-04-18_DESKTOP-F91JMJC/events.out.tfevents.1727802430.DESKTOP-F91JMJC.16788.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ca8bc3629b46f555de76810dc63958b0274b06bbe21f85249d44bd757b699f9
3
+ size 6987
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3aaf38279be2a01e1262488a4ca9deac9b42885e9251608e0e9fb81627b8002d
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2a8132d97c1e40166ef1ef15a63c289b17042cce027f61dd77c49b2822b845e
3
  size 5240