Hugging Face's logo

MelanieKoe
/
w2v2-base-pretrained_lr1e-4_at0.8_da0.9

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
MelanieKoe commited on
Commit
e062017
•
1 Parent(s): 6a09fcc

Model save

Browse files
Files changed (2) hide show
  1. README.md +20 -16
  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: 3.4350
21
- - Wer: 1.0
22
 
23
  ## Model description
24
 
@@ -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
- | 15.2367 | 2.44 | 100 | 3.7048 | 1.0 |
55
- | 3.2713 | 4.88 | 200 | 3.3895 | 1.0 |
56
- | 3.2139 | 7.32 | 300 | 3.3689 | 1.0 |
57
- | 3.1969 | 9.76 | 400 | 3.6049 | 1.0 |
58
- | 3.1872 | 12.2 | 500 | 3.3182 | 1.0 |
59
- | 3.1829 | 14.63 | 600 | 3.4524 | 1.0 |
60
- | 3.1919 | 17.07 | 700 | 3.3392 | 1.0 |
61
- | 3.1863 | 19.51 | 800 | 3.4291 | 1.0 |
62
- | 3.1789 | 21.95 | 900 | 3.3734 | 1.0 |
63
- | 3.1849 | 24.39 | 1000 | 3.4350 | 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: 2.2030
21
+ - Wer: 0.1756
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: 3500
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
54
+ | 15.3627 | 6.1 | 250 | 3.8053 | 1.0 |
55
+ | 3.1688 | 12.2 | 500 | 3.1948 | 1.0 |
56
+ | 2.7881 | 18.29 | 750 | 1.6319 | 1.0047 |
57
+ | 0.3364 | 24.39 | 1000 | 0.9451 | 0.2704 |
58
+ | 0.1193 | 30.49 | 1250 | 1.3362 | 0.2089 |
59
+ | 0.0741 | 36.59 | 1500 | 1.8263 | 0.1914 |
60
+ | 0.0511 | 42.68 | 1750 | 1.8832 | 0.1747 |
61
+ | 0.0369 | 48.78 | 2000 | 1.9675 | 0.1794 |
62
+ | 0.0256 | 54.88 | 2250 | 2.2933 | 0.1820 |
63
+ | 0.0194 | 60.98 | 2500 | 2.3546 | 0.1875 |
64
+ | 0.0151 | 67.07 | 2750 | 2.3144 | 0.1773 |
65
+ | 0.0126 | 73.17 | 3000 | 2.1852 | 0.1713 |
66
+ | 0.0104 | 79.27 | 3250 | 2.2503 | 0.1756 |
67
+ | 0.0095 | 85.37 | 3500 | 2.2030 | 0.1756 |
68
 
69
 
70
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f571709df12d7c45312335579d4cfa2988de0e2cc3d5eda2906c22cd1d4321dc
3
  size 377629528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72ea9529aadfd7813dab3685b62ad4b6bd1ccee210986adb76cc2d77ca1874dd
3
  size 377629528