Hugging Face's logo

spktsagar
/
wav2vec2-large-xls-r-300m-nepali-openslr

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Nepali
wav2vec2
Generated from Trainer
speech
openslr
nepali
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
spktsagar commited on
Commit
89b85c0
•
1 Parent(s): 27c259f

End of training

Browse files
Files changed (20) hide show
  1. checkpoint-4000/config.json +0 -108
  2. checkpoint-4000/optimizer.pt +0 -3
  3. checkpoint-4000/preprocessor_config.json +0 -10
  4. checkpoint-4000/pytorch_model.bin +0 -3
  5. checkpoint-4000/rng_state.pth +0 -3
  6. checkpoint-4000/scaler.pt +0 -3
  7. checkpoint-4000/scheduler.pt +0 -3
  8. checkpoint-4000/trainer_state.json +0 -91
  9. checkpoint-4000/training_args.bin +0 -3
  10. last-checkpoint/config.json +0 -108
  11. last-checkpoint/optimizer.pt +0 -3
  12. last-checkpoint/preprocessor_config.json +0 -10
  13. last-checkpoint/pytorch_model.bin +0 -3
  14. last-checkpoint/rng_state.pth +0 -3
  15. last-checkpoint/scaler.pt +0 -3
  16. last-checkpoint/scheduler.pt +0 -3
  17. last-checkpoint/trainer_state.json +0 -106
  18. last-checkpoint/training_args.bin +0 -3
  19. pytorch_model.bin +1 -1
  20. runs/Oct22_17-03-58_9e5f78d3a62d/events.out.tfevents.1666459123.9e5f78d3a62d.75.0 +2 -2
checkpoint-4000/config.json DELETED
@@ -1,108 +0,0 @@
1
- {
2
- "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
- "activation_dropout": 0.0,
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": 0.1,
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,
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": 0.0,
53
- "feat_quantizer_dropout": 0.0,
54
- "final_dropout": 0.0,
55
- "gradient_checkpointing": false,
56
- "hidden_act": "gelu",
57
- "hidden_dropout": 0.1,
58
- "hidden_size": 1024,
59
- "initializer_range": 0.02,
60
- "intermediate_size": 4096,
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": 0.075,
69
- "model_type": "wav2vec2",
70
- "num_adapter_layers": 3,
71
- "num_attention_heads": 16,
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": 24,
78
- "num_negatives": 100,
79
- "output_hidden_size": 1024,
80
- "pad_token_id": 0,
81
- "proj_codevector_dim": 768,
82
- "tdnn_dilation": [
83
- 1,
84
- 2,
85
- 3,
86
- 1,
87
- 1
88
- ],
89
- "tdnn_dim": [
90
- 512,
91
- 512,
92
- 512,
93
- 512,
94
- 1500
95
- ],
96
- "tdnn_kernel": [
97
- 5,
98
- 3,
99
- 3,
100
- 1,
101
- 1
102
- ],
103
- "torch_dtype": "float32",
104
- "transformers_version": "4.23.1",
105
- "use_weighted_layer_sum": false,
106
- "vocab_size": 81,
107
- "xvector_output_dim": 512
108
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-4000/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8856782379d9841ea57cff0b1fb5f3a69608f4cdf3644275cb728eea14a93b1
3
- size 2490723217
 
 
 
 
checkpoint-4000/preprocessor_config.json DELETED
@@ -1,10 +0,0 @@
1
- {
2
- "do_normalize": true,
3
- "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
- "feature_size": 1,
5
- "padding_side": "right",
6
- "padding_value": 0.0,
7
- "processor_class": "Wav2Vec2Processor",
8
- "return_attention_mask": true,
9
- "sampling_rate": 16000
10
- }
 
 
 
 
 
 
 
 
 
 
 
checkpoint-4000/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3abdc0ec372af4c1f0cb8fe2700d53bf89af31afa9ad345475241518e7b8a12a
3
- size 1262230833
 
 
 
 
checkpoint-4000/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c738b7f859d5e6b53da0038dd8a5906c1551e5a6c675bddd3d2e7aafe735fa53
3
- size 14503
 
 
 
 
checkpoint-4000/scaler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:103a680a2386bbc670e888e25d8d99d62e08eadb22cc712e28927456d447bd0a
3
- size 559
 
 
 
 
checkpoint-4000/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:be7187a44de05fd610cf3e045c79476f7ee186022afc0f3b38387494dcf9857a
3
- size 623
 
 
 
 
checkpoint-4000/trainer_state.json DELETED
@@ -1,91 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 1.0460190874624133,
5
- "global_step": 4000,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.21,
12
- "learning_rate": 0.0002976391096979332,
13
- "loss": 6.4525,
14
- "step": 800
15
- },
16
- {
17
- "epoch": 0.21,
18
- "eval_loss": 1.4264159202575684,
19
- "eval_runtime": 579.6055,
20
- "eval_samples_per_second": 37.262,
21
- "eval_steps_per_second": 4.658,
22
- "eval_wer": 0.9522086267891338,
23
- "step": 800
24
- },
25
- {
26
- "epoch": 0.42,
27
- "learning_rate": 0.00029127980922098566,
28
- "loss": 1.105,
29
- "step": 1600
30
- },
31
- {
32
- "epoch": 0.42,
33
- "eval_loss": 0.5966897010803223,
34
- "eval_runtime": 638.739,
35
- "eval_samples_per_second": 33.812,
36
- "eval_steps_per_second": 4.227,
37
- "eval_wer": 0.6514394209860115,
38
- "step": 1600
39
- },
40
- {
41
- "epoch": 0.63,
42
- "learning_rate": 0.00028492050874403814,
43
- "loss": 0.7933,
44
- "step": 2400
45
- },
46
- {
47
- "epoch": 0.63,
48
- "eval_loss": 0.44666677713394165,
49
- "eval_runtime": 578.27,
50
- "eval_samples_per_second": 37.348,
51
- "eval_steps_per_second": 4.669,
52
- "eval_wer": 0.5045276037778715,
53
- "step": 2400
54
- },
55
- {
56
- "epoch": 0.84,
57
- "learning_rate": 0.00027856120826709056,
58
- "loss": 0.6926,
59
- "step": 3200
60
- },
61
- {
62
- "epoch": 0.84,
63
- "eval_loss": 0.3889370858669281,
64
- "eval_runtime": 574.1787,
65
- "eval_samples_per_second": 37.614,
66
- "eval_steps_per_second": 4.702,
67
- "eval_wer": 0.4508941611762033,
68
- "step": 3200
69
- },
70
- {
71
- "epoch": 1.05,
72
- "learning_rate": 0.0002722019077901431,
73
- "loss": 0.6258,
74
- "step": 4000
75
- },
76
- {
77
- "epoch": 1.05,
78
- "eval_loss": 0.33456486463546753,
79
- "eval_runtime": 575.0581,
80
- "eval_samples_per_second": 37.556,
81
- "eval_steps_per_second": 4.695,
82
- "eval_wer": 0.39778001363149523,
83
- "step": 4000
84
- }
85
- ],
86
- "max_steps": 38240,
87
- "num_train_epochs": 10,
88
- "total_flos": 1.2716705617574113e+19,
89
- "trial_name": null,
90
- "trial_params": null
91
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-4000/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4033fcd8e67dce330e711cf22738b88ae3860329ea7760913077a6254b5968c9
3
- size 3439
 
 
 
 
last-checkpoint/config.json DELETED
@@ -1,108 +0,0 @@
1
- {
2
- "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
- "activation_dropout": 0.0,
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": 0.1,
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,
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": 0.0,
53
- "feat_quantizer_dropout": 0.0,
54
- "final_dropout": 0.0,
55
- "gradient_checkpointing": false,
56
- "hidden_act": "gelu",
57
- "hidden_dropout": 0.1,
58
- "hidden_size": 1024,
59
- "initializer_range": 0.02,
60
- "intermediate_size": 4096,
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": 0.075,
69
- "model_type": "wav2vec2",
70
- "num_adapter_layers": 3,
71
- "num_attention_heads": 16,
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": 24,
78
- "num_negatives": 100,
79
- "output_hidden_size": 1024,
80
- "pad_token_id": 0,
81
- "proj_codevector_dim": 768,
82
- "tdnn_dilation": [
83
- 1,
84
- 2,
85
- 3,
86
- 1,
87
- 1
88
- ],
89
- "tdnn_dim": [
90
- 512,
91
- 512,
92
- 512,
93
- 512,
94
- 1500
95
- ],
96
- "tdnn_kernel": [
97
- 5,
98
- 3,
99
- 3,
100
- 1,
101
- 1
102
- ],
103
- "torch_dtype": "float32",
104
- "transformers_version": "4.23.1",
105
- "use_weighted_layer_sum": false,
106
- "vocab_size": 81,
107
- "xvector_output_dim": 512
108
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a40fe4eb4646a99819376de89cad6d2f936e4fc21a42be155239db9665e214e9
3
- size 2490723217
 
 
 
 
last-checkpoint/preprocessor_config.json DELETED
@@ -1,10 +0,0 @@
1
- {
2
- "do_normalize": true,
3
- "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
- "feature_size": 1,
5
- "padding_side": "right",
6
- "padding_value": 0.0,
7
- "processor_class": "Wav2Vec2Processor",
8
- "return_attention_mask": true,
9
- "sampling_rate": 16000
10
- }
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5971caf93277533e76dd4eda4616a1d896c56fc4c8b77c374aa639938e7baca8
3
- size 1262230833
 
 
 
 
last-checkpoint/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c588b9e31769b33d78ed6785c4986e8911b719007af182ab911b44e91eaf1276
3
- size 14567
 
 
 
 
last-checkpoint/scaler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcf4d1a322767767fb41959a40e4c19029c6c19c14602f1e1a4cff6ab33492ec
3
- size 559
 
 
 
 
last-checkpoint/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc866df3ca7994652c92151602986956af84e29e8e900cc98047054e01623ceb
3
- size 623
 
 
 
 
last-checkpoint/trainer_state.json DELETED
@@ -1,106 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 1.2551967577461105,
5
- "global_step": 4800,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.21,
12
- "learning_rate": 0.0002976391096979332,
13
- "loss": 6.4525,
14
- "step": 800
15
- },
16
- {
17
- "epoch": 0.21,
18
- "eval_loss": 1.4264159202575684,
19
- "eval_runtime": 579.6055,
20
- "eval_samples_per_second": 37.262,
21
- "eval_steps_per_second": 4.658,
22
- "eval_wer": 0.9522086267891338,
23
- "step": 800
24
- },
25
- {
26
- "epoch": 0.42,
27
- "learning_rate": 0.00029127980922098566,
28
- "loss": 1.105,
29
- "step": 1600
30
- },
31
- {
32
- "epoch": 0.42,
33
- "eval_loss": 0.5966897010803223,
34
- "eval_runtime": 638.739,
35
- "eval_samples_per_second": 33.812,
36
- "eval_steps_per_second": 4.227,
37
- "eval_wer": 0.6514394209860115,
38
- "step": 1600
39
- },
40
- {
41
- "epoch": 0.63,
42
- "learning_rate": 0.00028492050874403814,
43
- "loss": 0.7933,
44
- "step": 2400
45
- },
46
- {
47
- "epoch": 0.63,
48
- "eval_loss": 0.44666677713394165,
49
- "eval_runtime": 578.27,
50
- "eval_samples_per_second": 37.348,
51
- "eval_steps_per_second": 4.669,
52
- "eval_wer": 0.5045276037778715,
53
- "step": 2400
54
- },
55
- {
56
- "epoch": 0.84,
57
- "learning_rate": 0.00027856120826709056,
58
- "loss": 0.6926,
59
- "step": 3200
60
- },
61
- {
62
- "epoch": 0.84,
63
- "eval_loss": 0.3889370858669281,
64
- "eval_runtime": 574.1787,
65
- "eval_samples_per_second": 37.614,
66
- "eval_steps_per_second": 4.702,
67
- "eval_wer": 0.4508941611762033,
68
- "step": 3200
69
- },
70
- {
71
- "epoch": 1.05,
72
- "learning_rate": 0.0002722019077901431,
73
- "loss": 0.6258,
74
- "step": 4000
75
- },
76
- {
77
- "epoch": 1.05,
78
- "eval_loss": 0.33456486463546753,
79
- "eval_runtime": 575.0581,
80
- "eval_samples_per_second": 37.556,
81
- "eval_steps_per_second": 4.695,
82
- "eval_wer": 0.39778001363149523,
83
- "step": 4000
84
- },
85
- {
86
- "epoch": 1.26,
87
- "learning_rate": 0.0002658426073131955,
88
- "loss": 0.5666,
89
- "step": 4800
90
- },
91
- {
92
- "epoch": 1.26,
93
- "eval_loss": 0.31256240606307983,
94
- "eval_runtime": 592.8115,
95
- "eval_samples_per_second": 36.431,
96
- "eval_steps_per_second": 4.555,
97
- "eval_wer": 0.3761481289149979,
98
- "step": 4800
99
- }
100
- ],
101
- "max_steps": 38240,
102
- "num_train_epochs": 10,
103
- "total_flos": 1.5254772631049953e+19,
104
- "trial_name": null,
105
- "trial_params": null
106
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:78f0314bc753f30b5d93d4be104533ba3cd7d837c7358b019a8ab73183149b42
3
- size 3439
 
 
 
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5971caf93277533e76dd4eda4616a1d896c56fc4c8b77c374aa639938e7baca8
3
  size 1262230833
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e762e563013625de12bbd685fa5782b363cdb75eb6a1f03c01b3bb901ebcaf20
3
  size 1262230833
runs/Oct22_17-03-58_9e5f78d3a62d/events.out.tfevents.1666459123.9e5f78d3a62d.75.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c067b75a6796def291003c3de3afc71c029ddb9ddcbb2d8743fc2d7e165d9a2
3
- size 5699
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8973e14e77898e659c5113ae590a6aa8bbeccf681b2c6ffcb61cda1f8d265ba8
3
+ size 6649