Hugging Face's logo

MelanieKoe
/
w2v2-base-pretrained_lr5e-5_at0.1_da1

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
MelanieKoe commited on
Commit
fb9737a
•
1 Parent(s): 46ec556

Model save

Browse files
Files changed (2) hide show
  1. README.md +21 -21
  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: 2.9860
21
- - Wer: 1.0
22
 
23
  ## Model description
24
 
@@ -43,30 +43,30 @@ 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
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Wer |
53
- |:-------------:|:-----:|:----:|:---------------:|:---:|
54
- | 20.8426 | 3.91 | 250 | 4.2781 | 1.0 |
55
- | 3.361 | 7.81 | 500 | 3.2598 | 1.0 |
56
- | 3.1516 | 11.72 | 750 | 3.1302 | 1.0 |
57
- | 3.0935 | 15.62 | 1000 | 3.1129 | 1.0 |
58
- | 3.0789 | 19.53 | 1250 | 3.0937 | 1.0 |
59
- | 3.074 | 23.44 | 1500 | 3.0938 | 1.0 |
60
- | 3.0673 | 27.34 | 1750 | 3.0927 | 1.0 |
61
- | 3.0709 | 31.25 | 2000 | 3.0861 | 1.0 |
62
- | 3.0482 | 35.16 | 2250 | 3.0659 | 1.0 |
63
- | 3.0259 | 39.06 | 2500 | 3.0543 | 1.0 |
64
- | 3.0173 | 42.97 | 2750 | 3.0568 | 1.0 |
65
- | 3.0072 | 46.88 | 3000 | 3.0708 | 1.0 |
66
- | 2.9967 | 50.78 | 3250 | 3.0357 | 1.0 |
67
- | 2.9757 | 54.69 | 3500 | 3.0239 | 1.0 |
68
- | 2.939 | 58.59 | 3750 | 3.0070 | 1.0 |
69
- | 2.8946 | 62.5 | 4000 | 2.9860 | 1.0 |
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: 1.1584
21
+ - Wer: 0.1683
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
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
54
+ | 19.3795 | 3.91 | 250 | 4.4039 | 1.0 |
55
+ | 3.4426 | 7.81 | 500 | 3.2239 | 1.0 |
56
+ | 3.1246 | 11.72 | 750 | 3.1005 | 1.0 |
57
+ | 2.3409 | 15.62 | 1000 | 1.0214 | 0.8765 |
58
+ | 0.6128 | 19.53 | 1250 | 0.6213 | 0.4643 |
59
+ | 0.3506 | 23.44 | 1500 | 0.6847 | 0.2409 |
60
+ | 0.2498 | 27.34 | 1750 | 0.7219 | 0.2055 |
61
+ | 0.1928 | 31.25 | 2000 | 0.9377 | 0.1730 |
62
+ | 0.1689 | 35.16 | 2250 | 1.0552 | 0.1794 |
63
+ | 0.1437 | 39.06 | 2500 | 0.9440 | 0.1756 |
64
+ | 0.1256 | 42.97 | 2750 | 1.1132 | 0.1721 |
65
+ | 0.1199 | 46.88 | 3000 | 1.1349 | 0.1777 |
66
+ | 0.1087 | 50.78 | 3250 | 1.0542 | 0.1781 |
67
+ | 0.1056 | 54.69 | 3500 | 1.1394 | 0.1696 |
68
+ | 0.1006 | 58.59 | 3750 | 1.1261 | 0.1696 |
69
+ | 0.0933 | 62.5 | 4000 | 1.1584 | 0.1683 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17d0530abf84b186d1a3e0092e40f3895442f70cf9b1bb6caa7374b1a8cb9c39
3
  size 377629528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf66ef28eada0197efc6d08a1713b9fa95ef432f0063c873958a9bd72759856f
3
  size 377629528