MelanieKoe commited on
Commit
c9332c6
1 Parent(s): 70b9b4f

Model save

Browse files
Files changed (2) hide show
  1. README.md +17 -13
  2. model.safetensors +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 None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 12.8113
21
  - Wer: 1.0
22
 
23
  ## Model description
@@ -43,24 +43,28 @@ The following hyperparameters were used during training:
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: 100
47
- - num_epochs: 200
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:----:|:---------------:|:---:|
54
- | 37.1788 | 20.0 | 100 | 23.0806 | 1.0 |
55
- | 11.3482 | 40.0 | 200 | 13.5769 | 1.0 |
56
- | 10.5677 | 60.0 | 300 | 12.7009 | 1.0 |
57
- | 10.7536 | 80.0 | 400 | 12.6362 | 1.0 |
58
- | 10.6197 | 100.0 | 500 | 12.0408 | 1.0 |
59
- | 10.6547 | 120.0 | 600 | 12.5815 | 1.0 |
60
- | 10.6467 | 140.0 | 700 | 12.3283 | 1.0 |
61
- | 10.7028 | 160.0 | 800 | 12.4376 | 1.0 |
62
- | 10.5508 | 180.0 | 900 | 12.7306 | 1.0 |
63
- | 10.5932 | 200.0 | 1000 | 12.8113 | 1.0 |
 
 
 
 
64
 
65
 
66
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 17.4872
21
  - Wer: 1.0
22
 
23
  ## Model description
 
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: 1000
47
+ - training_steps: 3500
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:----:|:---------------:|:---:|
54
+ | 37.4028 | 50.0 | 250 | 20.8788 | 1.0 |
55
+ | 15.6492 | 100.0 | 500 | 19.7127 | 1.0 |
56
+ | 16.1334 | 150.0 | 750 | 20.9635 | 1.0 |
57
+ | 20.9127 | 200.0 | 1000 | 17.5870 | 1.0 |
58
+ | 18.6712 | 250.0 | 1250 | 17.4758 | 1.0 |
59
+ | 18.5148 | 300.0 | 1500 | 17.4736 | 1.0 |
60
+ | 18.4769 | 350.0 | 1750 | 17.4742 | 1.0 |
61
+ | 18.5946 | 400.0 | 2000 | 17.5825 | 1.0 |
62
+ | 18.4632 | 450.0 | 2250 | 17.4559 | 1.0 |
63
+ | 18.3947 | 500.0 | 2500 | 17.4270 | 1.0 |
64
+ | 18.573 | 550.0 | 2750 | 17.5461 | 1.0 |
65
+ | 18.4756 | 600.0 | 3000 | 17.5971 | 1.0 |
66
+ | 18.4707 | 650.0 | 3250 | 17.5327 | 1.0 |
67
+ | 18.5019 | 700.0 | 3500 | 17.4872 | 1.0 |
68
 
69
 
70
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5491abdd1d0c3b58c8edef6c8c6f78887ad708763f9b361515aeba4d2466872d
3
  size 377629528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f5809a5ab84782b693e853897fd88fcb217a205bae5a32c6bc552ca3e345721
3
  size 377629528