Hugging Face's logo

Sambit20030731
/
sambit-workacc

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Community
Sambit20030731 commited on
Commit
15cb8d4
·
verified ·
1 Parent(s): 588cc28

End of training

Browse files
Files changed (3) hide show
  1. README.md +12 -6
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ 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 the PolyAI/minds14 dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 17.8165
21
  - Wer: 1.0
22
 
23
  ## Model description
@@ -46,17 +46,23 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 40
49
- - training_steps: 80
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:-----:|:----:|:---------------:|:------:|
56
- | No log | 0.8 | 20 | 45.9099 | 1.0365 |
57
- | 45.9757 | 1.6 | 40 | 36.6239 | 1.0041 |
58
- | 32.644 | 2.4 | 60 | 22.5639 | 1.0 |
59
- | 32.644 | 3.2 | 80 | 17.8165 | 1.0 |
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the PolyAI/minds14 dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 24.8037
21
  - Wer: 1.0
22
 
23
  ## Model description
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 40
49
+ - training_steps: 200
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:-----:|:----:|:---------------:|:------:|
56
+ | No log | 0.8 | 20 | 34.5760 | 1.0063 |
57
+ | 47.3781 | 1.6 | 40 | 24.8037 | 1.0 |
58
+ | 27.6882 | 2.4 | 60 | 8.2192 | 1.0 |
59
+ | 27.6882 | 3.2 | 80 | 4.0556 | 1.0 |
60
+ | 6.5092 | 4.0 | 100 | 3.6545 | 1.0 |
61
+ | 4.1312 | 4.8 | 120 | 3.5571 | 1.0 |
62
+ | 4.1312 | 5.6 | 140 | 3.5060 | 1.0 |
63
+ | 3.929 | 6.4 | 160 | 3.4571 | 1.0 |
64
+ | 3.8668 | 7.2 | 180 | 3.4330 | 1.0 |
65
+ | 3.8668 | 8.0 | 200 | 3.4136 | 1.0 |
66
 
67
 
68
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65c5069bef9719b35b99153878d64bf1d655223f2d2cc764e61cab8fdfa9d834
3
  size 377611120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c358ca9f34f866d5317ef9cb5a342005299a9729a3f85c307657aaf6a0cc5521
3
  size 377611120
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74bdc857adecb18c96a63048402771a46b06941b5761f5fecadb8c5f83c3a969
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:322f86eb507656e3df837966dbc33289136f9129697da7c0a9a67b4c3270c321
3
  size 4536