Hugging Face's logo

YoussefAshmawy
/
Graduation_Project_Whisper_base

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
arabic
quran
Eval Results
Model card Files
xet
Metrics Community
YoussefAshmawy commited on
Commit
dbccb1a
·
verified ·
1 Parent(s): e076e08

Training finished

Browse files
Files changed (3) hide show
  1. README.md +28 -28
  2. model.safetensors +1 -1
  3. runs/Dec26_15-51-47_0661992ba2c7/events.out.tfevents.1735256731.0661992ba2c7.23.1 +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-base](https://huggingface.co/openai/whisper-base) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0090
24
- - Wer: 0.1022
25
- - Cer: 0.0414
26
 
27
  ## Model description
28
 
@@ -57,31 +57,31 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
- | 0.0088 | 1.0 | 375 | 0.0076 | 0.0945 | 0.0386 |
61
- | 0.007 | 2.0 | 750 | 0.0109 | 0.1343 | 0.0498 |
62
- | 0.0039 | 3.0 | 1125 | 0.0115 | 0.1119 | 0.0385 |
63
- | 0.0026 | 4.0 | 1500 | 0.0125 | 0.1347 | 0.0570 |
64
- | 0.0016 | 5.0 | 1875 | 0.0133 | 0.1129 | 0.0410 |
65
- | 0.0014 | 6.0 | 2250 | 0.0134 | 0.1234 | 0.0461 |
66
- | 0.0014 | 7.0 | 2625 | 0.0131 | 0.1135 | 0.0397 |
67
- | 0.0013 | 8.0 | 3000 | 0.0137 | 0.1281 | 0.0523 |
68
- | 0.0011 | 9.0 | 3375 | 0.0135 | 0.1104 | 0.0383 |
69
- | 0.0007 | 10.0 | 3750 | 0.0142 | 0.1162 | 0.0425 |
70
- | 0.0005 | 11.0 | 4125 | 0.0139 | 0.1079 | 0.0391 |
71
- | 0.0004 | 12.0 | 4500 | 0.0134 | 0.1010 | 0.0409 |
72
- | 0.0005 | 13.0 | 4875 | 0.0150 | 0.1050 | 0.0379 |
73
- | 0.0005 | 14.0 | 5250 | 0.0161 | 0.1182 | 0.0460 |
74
- | 0.0003 | 15.0 | 5625 | 0.0149 | 0.1082 | 0.0390 |
75
- | 0.0001 | 16.0 | 6000 | 0.0154 | 0.1088 | 0.0379 |
76
- | 0.0001 | 17.0 | 6375 | 0.0156 | 0.1046 | 0.0362 |
77
- | 0.0001 | 18.0 | 6750 | 0.0148 | 0.1021 | 0.0357 |
78
- | 0.0 | 19.0 | 7125 | 0.0148 | 0.1010 | 0.0368 |
79
- | 0.0002 | 20.0 | 7500 | 0.0149 | 0.0995 | 0.0370 |
80
- | 0.0 | 21.0 | 7875 | 0.0149 | 0.1017 | 0.0374 |
81
- | 0.0 | 22.0 | 8250 | 0.0150 | 0.0988 | 0.0363 |
82
- | 0.0 | 23.0 | 8625 | 0.0150 | 0.0972 | 0.0356 |
83
- | 0.0 | 24.0 | 9000 | 0.0171 | 0.0999 | 0.0379 |
84
- | 0.0 | 25.0 | 9375 | 0.0151 | 0.0979 | 0.0362 |
85
 
86
 
87
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0180
24
+ - Wer: 0.1014
25
+ - Cer: 0.0388
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
+ | 0.0058 | 1.0 | 375 | 0.0084 | 0.1035 | 0.0367 |
61
+ | 0.0073 | 2.0 | 750 | 0.0121 | 0.1385 | 0.0461 |
62
+ | 0.0035 | 3.0 | 1125 | 0.0124 | 0.1394 | 0.0520 |
63
+ | 0.0029 | 4.0 | 1500 | 0.0128 | 0.1325 | 0.0530 |
64
+ | 0.0016 | 5.0 | 1875 | 0.0137 | 0.1175 | 0.0444 |
65
+ | 0.0015 | 6.0 | 2250 | 0.0145 | 0.1214 | 0.0475 |
66
+ | 0.0009 | 7.0 | 2625 | 0.0148 | 0.1227 | 0.0469 |
67
+ | 0.0013 | 8.0 | 3000 | 0.0143 | 0.1254 | 0.0485 |
68
+ | 0.0006 | 9.0 | 3375 | 0.0147 | 0.1173 | 0.0415 |
69
+ | 0.0007 | 10.0 | 3750 | 0.0153 | 0.1205 | 0.0427 |
70
+ | 0.0009 | 11.0 | 4125 | 0.0154 | 0.1064 | 0.0398 |
71
+ | 0.0005 | 12.0 | 4500 | 0.0157 | 0.1117 | 0.0398 |
72
+ | 0.0003 | 13.0 | 4875 | 0.0156 | 0.1046 | 0.0390 |
73
+ | 0.0002 | 14.0 | 5250 | 0.0159 | 0.1137 | 0.0463 |
74
+ | 0.0 | 15.0 | 5625 | 0.0166 | 0.1084 | 0.0434 |
75
+ | 0.0002 | 16.0 | 6000 | 0.0170 | 0.1137 | 0.0413 |
76
+ | 0.0002 | 17.0 | 6375 | 0.0164 | 0.1035 | 0.0385 |
77
+ | 0.0001 | 18.0 | 6750 | 0.0163 | 0.1086 | 0.0420 |
78
+ | 0.0 | 19.0 | 7125 | 0.0162 | 0.1039 | 0.0392 |
79
+ | 0.0 | 20.0 | 7500 | 0.0164 | 0.1008 | 0.0375 |
80
+ | 0.0 | 21.0 | 7875 | 0.0166 | 0.1010 | 0.0382 |
81
+ | 0.0 | 22.0 | 8250 | 0.0167 | 0.0999 | 0.0380 |
82
+ | 0.0 | 23.0 | 8625 | 0.0168 | 0.0990 | 0.0374 |
83
+ | 0.0 | 24.0 | 9000 | 0.0181 | 0.1012 | 0.0386 |
84
+ | 0.0 | 25.0 | 9375 | 0.0168 | 0.0992 | 0.0377 |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a98806edb04661b74c1f00859c242e6a886b6f0fa27fe879d76f6bdb7dc9a6c2
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e577d3f4a892b993de9c82651c8cd80dcc3a5a34bed2979b0bc20cacfd89897
3
  size 290403936
runs/Dec26_15-51-47_0661992ba2c7/events.out.tfevents.1735256731.0661992ba2c7.23.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8be04b25c2c72061c1828292d96f47d08008b603a53ae8a0666c644b3426c60d
3
+ size 453