Hugging Face's logo

Baselhany
/
fine_tune_Whisper_tiny2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Baselhany commited on
Commit
bdd1030
·
verified ·
1 Parent(s): 1001fc9

Training finished

Browse files
Files changed (3) hide show
  1. README.md +10 -12
  2. model.safetensors +1 -1
  3. runs/Jan18_22-44-17_8dda39b996ac/events.out.tfevents.1737249132.8dda39b996ac.18.1 +3 -0
README.md CHANGED
@@ -20,9 +20,9 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0096
24
- - Wer: 0.1101
25
- - Cer: 0.0435
26
 
27
  ## Model description
28
 
@@ -57,15 +57,13 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
- | 0.0074 | 1.0 | 313 | 0.0085 | 0.1014 | 0.0371 |
61
- | 0.0092 | 2.0 | 626 | 0.0080 | 0.1017 | 0.0360 |
62
- | 0.0038 | 3.0 | 939 | 0.0079 | 0.0961 | 0.0329 |
63
- | 0.0049 | 4.0 | 1252 | 0.0081 | 0.1006 | 0.0366 |
64
- | 0.0029 | 5.0 | 1565 | 0.0090 | 0.1023 | 0.0397 |
65
- | 0.0024 | 6.0 | 1878 | 0.0091 | 0.0909 | 0.0323 |
66
- | 0.0045 | 7.0 | 2191 | 0.0096 | 0.0967 | 0.0360 |
67
- | 0.0023 | 8.0 | 2504 | 0.0102 | 0.0999 | 0.0458 |
68
- | 0.0013 | 9.0 | 2817 | 0.0107 | 0.0956 | 0.0439 |
69
 
70
 
71
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0081
24
+ - Wer: 0.0932
25
+ - Cer: 0.0353
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
+ | 0.0078 | 1.0 | 313 | 0.0078 | 0.0986 | 0.0390 |
61
+ | 0.0069 | 2.0 | 626 | 0.0075 | 0.0963 | 0.0371 |
62
+ | 0.0037 | 3.0 | 939 | 0.0077 | 0.0910 | 0.0323 |
63
+ | 0.004 | 4.0 | 1252 | 0.0079 | 0.0885 | 0.0316 |
64
+ | 0.0027 | 5.0 | 1565 | 0.0087 | 0.0974 | 0.0398 |
65
+ | 0.0029 | 6.0 | 1878 | 0.0090 | 0.0898 | 0.0326 |
66
+ | 0.001 | 7.0 | 2191 | 0.0095 | 0.0919 | 0.0340 |
 
 
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ad460153e34f3b428ae7cc1059e85f65352ea2349875e7fe324b90431b86109
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ade065ad7a5110afe965d7ed39bb3a3860d99349d4f6c2802088777eecdcd16
3
  size 151061672
runs/Jan18_22-44-17_8dda39b996ac/events.out.tfevents.1737249132.8dda39b996ac.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5c891862c83cee1d50e6f4186dd035f950a3c51bd4e98c74ae15f905c559942
3
+ size 453