Hugging Face's logo

cantillation
/
whisper-small-he-teamim5

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Hebrew
whisper
hf-asr-leaderboard
Generated from Trainer
Model card Files Metrics Community
cantillation commited on
Commit
6806ad6
·
1 Parent(s): c8a87f2

End of training

Browse files
Files changed (3) hide show
  1. README.md +8 -8
  2. generation_config.json +42 -0
  3. runs/Nov03_12-29-12_f8de6f74b0b3/events.out.tfevents.1699014554.f8de6f74b0b3.284.5 +2 -2
README.md CHANGED
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.4775
24
- - Wer: 82.8205
25
 
26
  ## Model description
27
 
@@ -56,12 +56,12 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Wer |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
59
- | 1.8938 | 2.27 | 50 | 1.3121 | 174.7436 |
60
- | 0.9157 | 4.55 | 100 | 0.7200 | 104.1026 |
61
- | 0.4968 | 6.82 | 150 | 0.5385 | 96.9231 |
62
- | 0.293 | 9.09 | 200 | 0.4869 | 86.1538 |
63
- | 0.1535 | 11.36 | 250 | 0.4656 | 85.0 |
64
- | 0.0808 | 13.64 | 300 | 0.4775 | 82.8205 |
65
 
66
 
67
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.4955
24
+ - Wer: 81.1538
25
 
26
  ## Model description
27
 
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Wer |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
59
+ | 1.8944 | 2.27 | 50 | 1.3441 | 106.9231 |
60
+ | 0.9601 | 4.55 | 100 | 0.7752 | 104.2308 |
61
+ | 0.5514 | 6.82 | 150 | 0.5895 | 100.5128 |
62
+ | 0.3454 | 9.09 | 200 | 0.5149 | 97.1795 |
63
+ | 0.1951 | 11.36 | 250 | 0.4918 | 83.4615 |
64
+ | 0.1149 | 13.64 | 300 | 0.4955 | 81.1538 |
65
 
66
 
67
  ### Framework versions
generation_config.json CHANGED
@@ -1,4 +1,46 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "begin_suppress_tokens": [
3
  220,
4
  50257
 
1
  {
2
+ "alignment_heads": [
3
+ [
4
+ 5,
5
+ 3
6
+ ],
7
+ [
8
+ 5,
9
+ 9
10
+ ],
11
+ [
12
+ 8,
13
+ 0
14
+ ],
15
+ [
16
+ 8,
17
+ 4
18
+ ],
19
+ [
20
+ 8,
21
+ 7
22
+ ],
23
+ [
24
+ 8,
25
+ 8
26
+ ],
27
+ [
28
+ 9,
29
+ 0
30
+ ],
31
+ [
32
+ 9,
33
+ 7
34
+ ],
35
+ [
36
+ 9,
37
+ 9
38
+ ],
39
+ [
40
+ 10,
41
+ 5
42
+ ]
43
+ ],
44
  "begin_suppress_tokens": [
45
  220,
46
  50257
runs/Nov03_12-29-12_f8de6f74b0b3/events.out.tfevents.1699014554.f8de6f74b0b3.284.5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a78d11c6f8ae760eb5e07ab9d65e58b1113ec24288790ed4ec6bfb08fc710eb0
3
- size 6953
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffafff6731d4ea10f8344b51441705412d002e7a035b14577d177f3d17b6a699
3
+ size 8257