Hugging Face's logo

MelanieKoe
/
w2v2-base-pretrained_lr5e-5_at0.9_da1

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
MelanieKoe commited on
Commit
0fe70b7
•
1 Parent(s): e1ea01c

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: 2.0012
21
- - Wer: 0.1794
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
- | 15.834 | 6.1 | 250 | 3.6941 | 1.0 |
55
- | 3.1623 | 12.2 | 500 | 3.3447 | 1.0 |
56
- | 2.81 | 18.29 | 750 | 1.9439 | 0.9983 |
57
- | 0.4575 | 24.39 | 1000 | 1.2543 | 0.2499 |
58
- | 0.1302 | 30.49 | 1250 | 1.5064 | 0.2080 |
59
- | 0.0852 | 36.59 | 1500 | 1.5567 | 0.1995 |
60
- | 0.0618 | 42.68 | 1750 | 1.8019 | 0.1982 |
61
- | 0.0497 | 48.78 | 2000 | 1.8515 | 0.2025 |
62
- | 0.0395 | 54.88 | 2250 | 1.8758 | 0.1897 |
63
- | 0.0301 | 60.98 | 2500 | 1.7991 | 0.1850 |
64
- | 0.0275 | 67.07 | 2750 | 1.9686 | 0.1777 |
65
- | 0.0213 | 73.17 | 3000 | 1.8964 | 0.1884 |
66
- | 0.02 | 79.27 | 3250 | 1.9815 | 0.1854 |
67
- | 0.017 | 85.37 | 3500 | 2.0240 | 0.1790 |
68
- | 0.0157 | 91.46 | 3750 | 1.9606 | 0.1768 |
69
- | 0.0137 | 97.56 | 4000 | 2.0012 | 0.1794 |
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: 2.5021
21
+ - Wer: 0.1820
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
+ | 18.4753 | 6.1 | 250 | 4.2333 | 1.0 |
55
+ | 3.358 | 12.2 | 500 | 3.2161 | 1.0 |
56
+ | 3.108 | 18.29 | 750 | 3.1259 | 1.0 |
57
+ | 2.2419 | 24.39 | 1000 | 1.1771 | 0.7117 |
58
+ | 0.2791 | 30.49 | 1250 | 1.5708 | 0.2328 |
59
+ | 0.137 | 36.59 | 1500 | 1.7979 | 0.1961 |
60
+ | 0.0936 | 42.68 | 1750 | 2.0223 | 0.1948 |
61
+ | 0.0723 | 48.78 | 2000 | 2.2080 | 0.1892 |
62
+ | 0.0584 | 54.88 | 2250 | 2.1748 | 0.1854 |
63
+ | 0.0472 | 60.98 | 2500 | 2.2649 | 0.1828 |
64
+ | 0.042 | 67.07 | 2750 | 2.3289 | 0.1880 |
65
+ | 0.0349 | 73.17 | 3000 | 2.3042 | 0.1854 |
66
+ | 0.032 | 79.27 | 3250 | 2.2214 | 0.1841 |
67
+ | 0.0284 | 85.37 | 3500 | 2.3253 | 0.1807 |
68
+ | 0.0258 | 91.46 | 3750 | 2.4980 | 0.1815 |
69
+ | 0.0238 | 97.56 | 4000 | 2.5021 | 0.1820 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f19ab5a874b315e5f8b96237477dfb1aa433a93561644a294b9b8189ff0e19b1
3
  size 377629528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41cc44c7977bdb19c24a9daf8a14bab6753d4f19536f07f5e42c0e56a7711784
3
  size 377629528