Hugging Face's logo

MelanieKoe
/
w2v2-base-pretrained_lr5e-5_at0.8_da0.025

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
MelanieKoe commited on
Commit
75e0a67
•
1 Parent(s): b3847dc

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: 9.1596
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
- | 33.8202 | 125.0 | 250 | 47.1503 | 1.0 |
55
- | 11.5918 | 250.0 | 500 | 9.7965 | 1.0 |
56
- | 10.0921 | 375.0 | 750 | 9.2904 | 1.0 |
57
- | 6.6014 | 500.0 | 1000 | 9.2396 | 1.0 |
58
- | 7.8557 | 625.0 | 1250 | 9.2582 | 1.0 |
59
- | 7.6576 | 750.0 | 1500 | 10.7610 | 1.0 |
60
- | 7.0009 | 875.0 | 1750 | 9.2900 | 1.0 |
61
- | 6.6034 | 1000.0 | 2000 | 9.2763 | 1.0 |
62
- | 6.5928 | 1125.0 | 2250 | 9.2703 | 1.0 |
63
- | 6.5581 | 1250.0 | 2500 | 9.1374 | 1.0 |
64
- | 6.4663 | 1375.0 | 2750 | 9.1508 | 1.0 |
65
- | 6.4496 | 1500.0 | 3000 | 9.1802 | 1.0 |
66
- | 6.4061 | 1625.0 | 3250 | 9.1858 | 1.0 |
67
- | 6.4291 | 1750.0 | 3500 | 9.1535 | 1.0 |
68
- | 6.4131 | 1875.0 | 3750 | 9.1450 | 1.0 |
69
- | 6.4086 | 2000.0 | 4000 | 9.1596 | 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: 3.9947
21
+ - Wer: 1.0205
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
+ | 36.9594 | 125.0 | 250 | 12.4193 | 1.0 |
55
+ | 5.8739 | 250.0 | 500 | 3.2963 | 1.0 |
56
+ | 3.1532 | 375.0 | 750 | 3.1231 | 1.0 |
57
+ | 3.0639 | 500.0 | 1000 | 3.1060 | 1.0 |
58
+ | 3.013 | 625.0 | 1250 | 3.1074 | 1.0 |
59
+ | 2.9755 | 750.0 | 1500 | 3.1334 | 1.0 |
60
+ | 2.94 | 875.0 | 1750 | 3.1535 | 1.0 |
61
+ | 2.8802 | 1000.0 | 2000 | 3.0883 | 1.0 |
62
+ | 2.474 | 1125.0 | 2250 | 2.8111 | 1.0009 |
63
+ | 1.3378 | 1250.0 | 2500 | 3.0612 | 1.0038 |
64
+ | 0.7759 | 1375.0 | 2750 | 3.4681 | 1.0068 |
65
+ | 0.594 | 1500.0 | 3000 | 3.6791 | 1.0337 |
66
+ | 0.5034 | 1625.0 | 3250 | 3.8161 | 1.0226 |
67
+ | 0.4518 | 1750.0 | 3500 | 3.8285 | 1.0081 |
68
+ | 0.4139 | 1875.0 | 3750 | 3.9486 | 1.0201 |
69
+ | 0.3953 | 2000.0 | 4000 | 3.9947 | 1.0205 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a823257655e33237409724823d0bdfd342224378a8294570ec4c07453793157
3
  size 377629528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57deba99fe08161bf80ffefe59f8e714cfae25ac0ff2425ff2b1bba9ced7b4d4
3
  size 377629528