Hugging Face's logo

MelanieKoe
/
w2v2-base-pretrained_lr5e-5_at0.8_da0.05

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
MelanieKoe commited on
Commit
569abcb
•
1 Parent(s): d8ef120

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: 4.9499
21
- - Wer: 1.1098
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
- | 32.094 | 83.33 | 250 | 3.6861 | 1.0 |
55
- | 3.223 | 166.67 | 500 | 3.1064 | 1.0 |
56
- | 3.0141 | 250.0 | 750 | 3.0722 | 1.0 |
57
- | 2.6901 | 333.33 | 1000 | 2.8675 | 1.0 |
58
- | 1.7283 | 416.67 | 1250 | 3.2044 | 1.0436 |
59
- | 0.9791 | 500.0 | 1500 | 3.4905 | 1.0666 |
60
- | 0.6506 | 583.33 | 1750 | 3.7132 | 1.0560 |
61
- | 0.3895 | 666.67 | 2000 | 4.1587 | 1.0824 |
62
- | 0.2399 | 750.0 | 2250 | 4.4319 | 1.1012 |
63
- | 0.1794 | 833.33 | 2500 | 4.4773 | 1.0995 |
64
- | 0.139 | 916.67 | 2750 | 4.6309 | 1.0871 |
65
- | 0.1026 | 1000.0 | 3000 | 4.6925 | 1.0628 |
66
- | 0.0807 | 1083.33 | 3250 | 4.8052 | 1.0824 |
67
- | 0.0611 | 1166.67 | 3500 | 4.8086 | 1.0953 |
68
- | 0.0539 | 1250.0 | 3750 | 4.8570 | 1.0995 |
69
- | 0.0524 | 1333.33 | 4000 | 4.9499 | 1.1098 |
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: 3.9827
21
+ - Wer: 1.0295
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
+ | 43.0808 | 83.33 | 250 | 28.8440 | 1.0 |
55
+ | 8.5391 | 166.67 | 500 | 3.7744 | 1.0 |
56
+ | 3.2564 | 250.0 | 750 | 3.1400 | 1.0 |
57
+ | 3.0586 | 333.33 | 1000 | 3.1144 | 1.0 |
58
+ | 2.9982 | 416.67 | 1250 | 3.0792 | 1.0 |
59
+ | 2.927 | 500.0 | 1500 | 3.0777 | 1.0 |
60
+ | 2.7925 | 583.33 | 1750 | 3.0732 | 1.0 |
61
+ | 2.577 | 666.67 | 2000 | 3.0084 | 1.0 |
62
+ | 2.2523 | 750.0 | 2250 | 2.9828 | 1.0 |
63
+ | 1.8719 | 833.33 | 2500 | 3.1056 | 1.0026 |
64
+ | 1.5177 | 916.67 | 2750 | 3.3320 | 1.0154 |
65
+ | 1.233 | 1000.0 | 3000 | 3.5057 | 1.0184 |
66
+ | 1.0527 | 1083.33 | 3250 | 3.7065 | 1.0325 |
67
+ | 0.9262 | 1166.67 | 3500 | 3.8646 | 1.0316 |
68
+ | 0.8456 | 1250.0 | 3750 | 3.9958 | 1.0295 |
69
+ | 0.8247 | 1333.33 | 4000 | 3.9827 | 1.0295 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f8a210b4aad4267742c746453b008b5ee050c3da7ac2a0e19e64c6537c69d4c
3
  size 377629528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6239f56e328e6938cbb2d46df00047c8da044e8955c3f89a653b0849af0160a9
3
  size 377629528