Hugging Face's logo

Baselhany
/
Graduation_Project_Whisper_tiny3

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
Baselhany commited on
Commit
0348518
·
verified ·
1 Parent(s): dd0edc2

Training finished

Browse files
Files changed (3) hide show
  1. README.md +24 -24
  2. model.safetensors +1 -1
  3. runs/Feb09_07-48-20_f26e695a8b40/events.out.tfevents.1739110961.f26e695a8b40.18.1 +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: 0.0148
24
- - Wer: 0.0829
25
- - Cer: 0.0324
26
 
27
  ## Model description
28
 
@@ -41,7 +41,7 @@ More information needed
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
- - learning_rate: 0.0001
45
  - train_batch_size: 16
46
  - eval_batch_size: 16
47
  - seed: 42
@@ -57,26 +57,26 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
60
- | 0.0107 | 1.0 | 157 | 0.0086 | 0.0889 | 0.0338 |
61
- | 0.0069 | 2.0 | 314 | 0.0084 | 0.0896 | 0.0353 |
62
- | 0.0042 | 3.0 | 471 | 0.0102 | 0.1070 | 0.0380 |
63
- | 0.004 | 4.0 | 628 | 0.0111 | 0.1135 | 0.0406 |
64
- | 0.0029 | 5.0 | 785 | 0.0118 | 0.1086 | 0.0401 |
65
- | 0.0023 | 6.0 | 942 | 0.0128 | 0.1082 | 0.0388 |
66
- | 0.0017 | 7.0 | 1099 | 0.0125 | 0.1033 | 0.0375 |
67
- | 0.0013 | 8.0 | 1256 | 0.0133 | 0.1073 | 0.0383 |
68
- | 0.0009 | 9.0 | 1413 | 0.0133 | 0.1084 | 0.0376 |
69
- | 0.0007 | 10.0 | 1570 | 0.0134 | 0.1024 | 0.0375 |
70
- | 0.0005 | 11.0 | 1727 | 0.0142 | 0.1024 | 0.0358 |
71
- | 0.0004 | 12.0 | 1884 | 0.0132 | 0.0988 | 0.0331 |
72
- | 0.0003 | 13.0 | 2041 | 0.0137 | 0.0952 | 0.0337 |
73
- | 0.0001 | 14.0 | 2198 | 0.0144 | 0.0972 | 0.0350 |
74
- | 0.0001 | 15.0 | 2355 | 0.0135 | 0.0927 | 0.0338 |
75
- | 0.0 | 16.0 | 2512 | 0.0136 | 0.0934 | 0.0339 |
76
- | 0.0 | 17.0 | 2669 | 0.0134 | 0.0871 | 0.0313 |
77
- | 0.0 | 18.0 | 2826 | 0.0134 | 0.0833 | 0.0307 |
78
- | 0.0 | 19.0 | 2983 | 0.0145 | 0.0841 | 0.0358 |
79
- | 0.0 | 19.8768 | 3120 | 0.0139 | 0.0782 | 0.0296 |
80
 
81
 
82
  ### 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: 0.0086
24
+ - Wer: 0.0799
25
+ - Cer: 0.0319
26
 
27
  ## Model description
28
 
 
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
+ - learning_rate: 1e-05
45
  - train_batch_size: 16
46
  - eval_batch_size: 16
47
  - seed: 42
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
60
+ | 0.0108 | 1.0 | 157 | 0.0129 | 0.0771 | 0.0289 |
61
+ | 0.0124 | 2.0 | 314 | 0.0113 | 0.0758 | 0.0293 |
62
+ | 0.0083 | 3.0 | 471 | 0.0082 | 0.0767 | 0.0300 |
63
+ | 0.0053 | 4.0 | 628 | 0.0078 | 0.0742 | 0.0302 |
64
+ | 0.0037 | 5.0 | 785 | 0.0084 | 0.0706 | 0.0282 |
65
+ | 0.0019 | 6.0 | 942 | 0.0093 | 0.0719 | 0.0276 |
66
+ | 0.0013 | 7.0 | 1099 | 0.0102 | 0.0708 | 0.0289 |
67
+ | 0.0005 | 8.0 | 1256 | 0.0109 | 0.0744 | 0.0370 |
68
+ | 0.0002 | 9.0 | 1413 | 0.0112 | 0.0744 | 0.0369 |
69
+ | 0.0001 | 10.0 | 1570 | 0.0116 | 0.0742 | 0.0371 |
70
+ | 0.0 | 11.0 | 1727 | 0.0119 | 0.0728 | 0.0374 |
71
+ | 0.0 | 12.0 | 1884 | 0.0122 | 0.0748 | 0.0378 |
72
+ | 0.0 | 13.0 | 2041 | 0.0124 | 0.0782 | 0.0377 |
73
+ | 0.0 | 14.0 | 2198 | 0.0127 | 0.0762 | 0.0366 |
74
+ | 0.0 | 15.0 | 2355 | 0.0130 | 0.0771 | 0.0369 |
75
+ | 0.0 | 16.0 | 2512 | 0.0133 | 0.0871 | 0.0357 |
76
+ | 0.0 | 17.0 | 2669 | 0.0135 | 0.0863 | 0.0362 |
77
+ | 0.0 | 18.0 | 2826 | 0.0137 | 0.0782 | 0.0293 |
78
+ | 0.0 | 19.0 | 2983 | 0.0141 | 0.0800 | 0.0310 |
79
+ | 0.0 | 19.8768 | 3120 | 0.0138 | 0.0776 | 0.0295 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9582e0cf9d2c94a432ddc8cc4566d73bd73e302c056024dec0f54a058903c765
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa58cd8690b5c91aa6170b6dab561d4cbf295062fc53a4c0d3d54907ee6a21b
3
  size 151061672
runs/Feb09_07-48-20_f26e695a8b40/events.out.tfevents.1739110961.f26e695a8b40.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9212c6b56ea1dd16a4a38a225d6c5aed1aed445428bba25922d4c7bce8fa146e
3
+ size 453