Hugging Face's logo

Imxxn
/
AudioCourseU5-ASR

Automatic Speech Recognition
Transformers
PyTorch
whisper
Generated from Trainer
Inference Endpoints
Model card Files Community
Imxxn commited on
Commit
3f2cebb
·
1 Parent(s): 9e6ef3a

End of training

Browse files
Files changed (3) hide show
  1. README.md +11 -9
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -8,8 +8,6 @@ metrics:
8
  model-index:
9
  - name: AudioCourseU5-ASR
10
  results: []
11
- datasets:
12
- - PolyAI/minds14
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -19,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.6509
23
- - Wer Ortho: 34.5466
24
- - Wer: 34.1204
25
 
26
  ## Model description
27
 
@@ -51,9 +49,13 @@ The following hyperparameters were used during training:
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
55
- |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
56
- | 0.0007 | 17.86 | 500 | 0.6509 | 34.5466 | 34.1204 |
 
 
 
 
57
 
58
 
59
  ### Framework versions
@@ -61,4 +63,4 @@ The following hyperparameters were used during training:
61
  - Transformers 4.32.1
62
  - Pytorch 2.0.1+cu118
63
  - Datasets 2.14.4
64
- - Tokenizers 0.13.3
 
8
  model-index:
9
  - name: AudioCourseU5-ASR
10
  results: []
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
17
 
18
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.6438
21
+ - Wer Ortho: 34.4849
22
+ - Wer: 0.3406
23
 
24
  ## Model description
25
 
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
53
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
54
+ | 0.3065 | 3.57 | 100 | 0.4921 | 36.8908 | 0.3577 |
55
+ | 0.0391 | 7.14 | 200 | 0.5425 | 35.3486 | 0.3436 |
56
+ | 0.0042 | 10.71 | 300 | 0.5878 | 35.6570 | 0.3495 |
57
+ | 0.0012 | 14.29 | 400 | 0.6206 | 34.2998 | 0.3377 |
58
+ | 0.0007 | 17.86 | 500 | 0.6438 | 34.4849 | 0.3406 |
59
 
60
 
61
  ### Framework versions
 
63
  - Transformers 4.32.1
64
  - Pytorch 2.0.1+cu118
65
  - Datasets 2.14.4
66
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:042f09a4dbe5bce22b5af3fc127d7b9b70f03ad2d699462d83869f1495538973
3
  size 151099049
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed191115861876b60c6717ce5df7319915ff152719fd26794ffdcec83a21bda9
3
  size 151099049
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:405649297f1f5ffb402a161e722986228ca9e70edb51627a8655df0f4048bb43
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c577e253aea310e1315d21dccb3d7793b31d3e991dabe4400d415414deff2a6d
3
  size 4219