Hugging Face's logo

krishi0311
/
krishivoice

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
krishi0311 commited on
Commit
83aff93
•
1 Parent(s): c0c90bf

End of training

Browse files
Files changed (4) hide show
  1. README.md +20 -16
  2. model.safetensors +1 -1
  3. runs/Jun18_12-31-41_6a8b56242bfe/events.out.tfevents.1718713943.6a8b56242bfe.272.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
- base_model: facebook/wav2vec2-base
6
  metrics:
7
  - wer
8
  model-index:
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.4807
21
- - Wer: 0.7846
22
 
23
  ## Model description
24
 
@@ -37,27 +37,31 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 1e-05
41
- - train_batch_size: 20
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - lr_scheduler_warmup_steps: 500
47
- - num_epochs: 90
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Wer |
53
- |:-------------:|:-------:|:----:|:---------------:|:------:|
54
- | 3.0074 | 11.3636 | 500 | 3.6612 | 1.0 |
55
- | 2.9103 | 22.7273 | 1000 | 3.2488 | 1.0 |
56
- | 2.8471 | 34.0909 | 1500 | 3.0912 | 1.0 |
57
- | 2.2661 | 45.4545 | 2000 | 2.4130 | 0.9951 |
58
- | 1.4007 | 56.8182 | 2500 | 1.9495 | 0.8854 |
59
- | 1.0587 | 68.1818 | 3000 | 1.6888 | 0.8167 |
60
- | 0.9269 | 79.5455 | 3500 | 1.4807 | 0.7846 |
 
 
 
 
61
 
62
 
63
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: facebook/wav2vec2-base
4
  tags:
5
  - generated_from_trainer
 
6
  metrics:
7
  - wer
8
  model-index:
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.6148
21
+ - Wer: 0.2809
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 0.0001
41
+ - train_batch_size: 8
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 200
47
+ - num_epochs: 100
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|
54
+ | 0.3768 | 9.0909 | 1000 | 0.5920 | 0.4378 |
55
+ | 0.1392 | 18.1818 | 2000 | 0.5513 | 0.3537 |
56
+ | 0.0823 | 27.2727 | 3000 | 0.5021 | 0.3260 |
57
+ | 0.0566 | 36.3636 | 4000 | 0.5473 | 0.3163 |
58
+ | 0.0886 | 45.4545 | 5000 | 0.5637 | 0.3098 |
59
+ | 0.0368 | 54.5455 | 6000 | 0.5558 | 0.3004 |
60
+ | 0.0264 | 63.6364 | 7000 | 0.6315 | 0.2919 |
61
+ | 0.0214 | 72.7273 | 8000 | 0.5927 | 0.2902 |
62
+ | 0.0124 | 81.8182 | 9000 | 0.6936 | 0.2874 |
63
+ | 0.0132 | 90.9091 | 10000 | 0.6311 | 0.2858 |
64
+ | 0.0094 | 100.0 | 11000 | 0.6148 | 0.2809 |
65
 
66
 
67
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:315482181bbf863e97233e1c0eccedbe7b44b5da8dae674fe6884795aef2d697
3
  size 377611120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b84ecf4ce96692fac6419c2f9b8b01641c2c299cf67253b1029375c62a1f27a
3
  size 377611120
runs/Jun18_12-31-41_6a8b56242bfe/events.out.tfevents.1718713943.6a8b56242bfe.272.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:724b319ed2bc653df2b8bf2e35a16e2a013046f802f79a5153cc053afc718e15
3
+ size 33589
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddd8a3c7a968d2bf49018869398d46de8861840fcd361c110aa47412fdcacedd
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e601b39d71e32df76e19da1da771318b42c0f9d9f43c98bc91b573101cbdbbe
3
  size 5112