Hugging Face's logo

kosamit
/
whisper-tiny-ja-alicia

Automatic Speech Recognition
Transformers
PyTorch
whisper
Generated from Trainer
Inference Endpoints
Model card Files Community
kosamit commited on
Commit
8a6b299
•
1 Parent(s): 0a74f4a

Model save

Browse files
Files changed (3) hide show
  1. README.md +7 -8
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model was trained from scratch on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.8342
19
  - Wer: 85.7143
20
 
21
  ## Model description
@@ -41,18 +41,17 @@ The following hyperparameters were used during training:
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
- - lr_scheduler_warmup_steps: 20
45
- - training_steps: 100
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Wer |
50
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
51
- | 0.448 | 6.67 | 20 | 0.3697 | 85.7143 |
52
- | 0.003 | 13.33 | 40 | 0.7499 | 85.7143 |
53
- | 0.0 | 20.0 | 60 | 0.8176 | 85.7143 |
54
- | 0.0 | 26.67 | 80 | 0.8309 | 85.7143 |
55
- | 0.0 | 33.33 | 100 | 0.8342 | 85.7143 |
56
 
57
 
58
  ### Framework versions
 
15
 
16
  This model was trained from scratch on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.5542
19
  - Wer: 85.7143
20
 
21
  ## Model description
 
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 10
45
+ - training_steps: 40
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Wer |
50
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
51
+ | 0.0311 | 3.33 | 10 | 0.3741 | 85.7143 |
52
+ | 0.0012 | 6.67 | 20 | 0.4759 | 85.7143 |
53
+ | 0.0001 | 10.0 | 30 | 0.5351 | 85.7143 |
54
+ | 0.0 | 13.33 | 40 | 0.5542 | 85.7143 |
 
55
 
56
 
57
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:900b9e6457f37d99774d7be9864dabe1bb6099c8cdd93ec025add8825b768000
3
  size 151099494
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef7e2265100255bf580f73085cb8a36e54844cadd46d3a3ed8bdcd478a30cd58
3
  size 151099494
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:496e3c6aea7ec836ec19dab3aaed26ca295f08def6d3fd8894d8488db672bbe0
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f19d17e61a415bf1b492822a337041aa96f036d477af28b157e932d0a78e708
3
  size 4664