Hugging Face's logo

MelanieKoe
/
w2v2-base-pretrained_lr5e-5_at0.3_da1

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
MelanieKoe commited on
Commit
f44dfc6
•
1 Parent(s): bc5a6c8

Model save

Browse files
Files changed (2) hide show
  1. README.md +19 -19
  2. model.safetensors +1 -1
README.md CHANGED
@@ -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 the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.2363
21
- - Wer: 0.1773
22
 
23
  ## Model description
24
 
@@ -43,7 +43,7 @@ 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: 500
47
  - training_steps: 4000
48
  - mixed_precision_training: Native AMP
49
 
@@ -51,22 +51,22 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:----:|:---------------:|:------:|
54
- | 15.0228 | 3.97 | 250 | 4.0018 | 1.0 |
55
- | 3.1757 | 7.94 | 500 | 3.2733 | 1.0 |
56
- | 3.0888 | 11.9 | 750 | 3.0842 | 1.0 |
57
- | 1.8583 | 15.87 | 1000 | 0.8173 | 0.6087 |
58
- | 0.3832 | 19.84 | 1250 | 0.6533 | 0.3520 |
59
- | 0.2105 | 23.81 | 1500 | 0.7165 | 0.2448 |
60
- | 0.1301 | 27.78 | 1750 | 0.9040 | 0.2016 |
61
- | 0.0917 | 31.75 | 2000 | 1.0631 | 0.1961 |
62
- | 0.0674 | 35.71 | 2250 | 1.0216 | 0.1905 |
63
- | 0.0571 | 39.68 | 2500 | 1.1088 | 0.1854 |
64
- | 0.0456 | 43.65 | 2750 | 1.2525 | 0.1747 |
65
- | 0.0387 | 47.62 | 3000 | 1.1236 | 0.1845 |
66
- | 0.034 | 51.59 | 3250 | 1.1696 | 0.1730 |
67
- | 0.0291 | 55.56 | 3500 | 1.2542 | 0.1756 |
68
- | 0.0284 | 59.52 | 3750 | 1.2190 | 0.1760 |
69
- | 0.026 | 63.49 | 4000 | 1.2363 | 0.1773 |
70
 
71
 
72
  ### 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: 1.4352
21
+ - Wer: 0.1704
22
 
23
  ## Model description
24
 
 
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: 4000
48
  - mixed_precision_training: Native AMP
49
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:----:|:---------------:|:------:|
54
+ | 19.6725 | 3.97 | 250 | 4.9409 | 1.0 |
55
+ | 3.5043 | 7.94 | 500 | 3.2414 | 1.0 |
56
+ | 3.1162 | 11.9 | 750 | 3.1351 | 1.0 |
57
+ | 2.2138 | 15.87 | 1000 | 0.9146 | 0.9184 |
58
+ | 0.5308 | 19.84 | 1250 | 0.6292 | 0.4357 |
59
+ | 0.2762 | 23.81 | 1500 | 0.8713 | 0.2384 |
60
+ | 0.1894 | 27.78 | 1750 | 0.9537 | 0.1905 |
61
+ | 0.1339 | 31.75 | 2000 | 1.2355 | 0.1824 |
62
+ | 0.1002 | 35.71 | 2250 | 1.2193 | 0.1739 |
63
+ | 0.0858 | 39.68 | 2500 | 1.1557 | 0.1709 |
64
+ | 0.0711 | 43.65 | 2750 | 1.3591 | 0.1692 |
65
+ | 0.0589 | 47.62 | 3000 | 1.3372 | 0.1683 |
66
+ | 0.0525 | 51.59 | 3250 | 1.4133 | 0.1683 |
67
+ | 0.0464 | 55.56 | 3500 | 1.4969 | 0.1679 |
68
+ | 0.0436 | 59.52 | 3750 | 1.4262 | 0.1674 |
69
+ | 0.0401 | 63.49 | 4000 | 1.4352 | 0.1704 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e34ffceaaebb8590c2f74062cdaae8892a617215d78ce455287d6bfce8e07278
3
  size 377629528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cb80ac2fa0cfdec88dd7c489ee86f01cc563f35aedd24e919a0b1b482b98595
3
  size 377629528