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
00a0672
·
verified ·
1 Parent(s): 70a0c64

Training finished

Browse files
Files changed (4) hide show
  1. README.md +30 -30
  2. model.safetensors +1 -1
  3. runs/Mar11_15-23-41_1e4e0d7704d7/events.out.tfevents.1741706624.1e4e0d7704d7.23.0 +2 -2
  4. runs/Mar11_15-23-41_1e4e0d7704d7/events.out.tfevents.1741731835.1e4e0d7704d7.23.1 +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: 0.0037
24
- - Wer: 0.0560
25
- - Cer: 0.0223
26
 
27
  ## Model description
28
 
@@ -55,33 +55,33 @@ The following hyperparameters were used during training:
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
- |:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
60
- | 0.0037 | 0.9991 | 581 | 0.0038 | 0.0523 | 0.0206 |
61
- | 0.0019 | 2.0 | 1163 | 0.0042 | 0.0556 | 0.0202 |
62
- | 0.0006 | 2.9991 | 1744 | 0.0048 | 0.0547 | 0.0224 |
63
- | 0.0009 | 4.0 | 2326 | 0.0058 | 0.0630 | 0.0246 |
64
- | 0.001 | 4.9991 | 2907 | 0.0062 | 0.0652 | 0.0225 |
65
- | 0.0007 | 6.0 | 3489 | 0.0063 | 0.0653 | 0.0238 |
66
- | 0.0003 | 6.9991 | 4070 | 0.0059 | 0.0588 | 0.0216 |
67
- | 0.0002 | 8.0 | 4652 | 0.0055 | 0.0635 | 0.0247 |
68
- | 0.0002 | 8.9991 | 5233 | 0.0063 | 0.0599 | 0.0206 |
69
- | 0.0002 | 10.0 | 5815 | 0.0060 | 0.0597 | 0.0220 |
70
- | 0.0004 | 10.9991 | 6396 | 0.0063 | 0.0606 | 0.0219 |
71
- | 0.0002 | 12.0 | 6978 | 0.0068 | 0.0581 | 0.0226 |
72
- | 0.0001 | 12.9991 | 7559 | 0.0065 | 0.0601 | 0.0209 |
73
- | 0.0001 | 14.0 | 8141 | 0.0067 | 0.0559 | 0.0215 |
74
- | 0.0001 | 14.9991 | 8722 | 0.0066 | 0.0586 | 0.0217 |
75
- | 0.0 | 16.0 | 9304 | 0.0070 | 0.0592 | 0.0244 |
76
- | 0.0 | 16.9991 | 9885 | 0.0070 | 0.0579 | 0.0247 |
77
- | 0.0 | 18.0 | 10467 | 0.0072 | 0.0552 | 0.0231 |
78
- | 0.0 | 18.9991 | 11048 | 0.0073 | 0.0541 | 0.0229 |
79
- | 0.0 | 20.0 | 11630 | 0.0074 | 0.0539 | 0.0229 |
80
- | 0.0 | 20.9991 | 12211 | 0.0075 | 0.0532 | 0.0219 |
81
- | 0.0 | 22.0 | 12793 | 0.0076 | 0.0536 | 0.0223 |
82
- | 0.0 | 22.9991 | 13374 | 0.0077 | 0.0536 | 0.0223 |
83
- | 0.0 | 24.0 | 13956 | 0.0072 | 0.0560 | 0.0237 |
84
- | 0.0 | 24.9785 | 14525 | 0.0077 | 0.0536 | 0.0224 |
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: 0.0033
24
+ - Wer: 0.0497
25
+ - Cer: 0.0200
26
 
27
  ## Model description
28
 
 
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
+ | 0.0024 | 1.0 | 320 | 0.0034 | 0.0440 | 0.0180 |
61
+ | 0.0014 | 2.0 | 640 | 0.0049 | 0.0653 | 0.0257 |
62
+ | 0.0013 | 3.0 | 960 | 0.0057 | 0.0766 | 0.0283 |
63
+ | 0.0007 | 4.0 | 1280 | 0.0057 | 0.0681 | 0.0290 |
64
+ | 0.0004 | 5.0 | 1600 | 0.0057 | 0.0617 | 0.0253 |
65
+ | 0.0002 | 6.0 | 1920 | 0.0060 | 0.0662 | 0.0244 |
66
+ | 0.0002 | 7.0 | 2240 | 0.0068 | 0.0624 | 0.0237 |
67
+ | 0.0003 | 8.0 | 2560 | 0.0061 | 0.0652 | 0.0259 |
68
+ | 0.0003 | 9.0 | 2880 | 0.0067 | 0.0648 | 0.0252 |
69
+ | 0.0004 | 10.0 | 3200 | 0.0062 | 0.0670 | 0.0259 |
70
+ | 0.0002 | 11.0 | 3520 | 0.0061 | 0.0610 | 0.0230 |
71
+ | 0.0001 | 12.0 | 3840 | 0.0064 | 0.0581 | 0.0217 |
72
+ | 0.0001 | 13.0 | 4160 | 0.0061 | 0.0576 | 0.0217 |
73
+ | 0.0 | 14.0 | 4480 | 0.0062 | 0.0594 | 0.0235 |
74
+ | 0.0 | 15.0 | 4800 | 0.0066 | 0.0630 | 0.0251 |
75
+ | 0.0 | 16.0 | 5120 | 0.0069 | 0.0581 | 0.0240 |
76
+ | 0.0 | 17.0 | 5440 | 0.0070 | 0.0579 | 0.0228 |
77
+ | 0.0 | 18.0 | 5760 | 0.0071 | 0.0586 | 0.0232 |
78
+ | 0.0 | 19.0 | 6080 | 0.0072 | 0.0590 | 0.0239 |
79
+ | 0.0 | 20.0 | 6400 | 0.0072 | 0.0576 | 0.0234 |
80
+ | 0.0 | 21.0 | 6720 | 0.0073 | 0.0574 | 0.0239 |
81
+ | 0.0 | 22.0 | 7040 | 0.0073 | 0.0577 | 0.0240 |
82
+ | 0.0 | 23.0 | 7360 | 0.0074 | 0.0577 | 0.0240 |
83
+ | 0.0 | 24.0 | 7680 | 0.0076 | 0.0613 | 0.0246 |
84
+ | 0.0 | 25.0 | 8000 | 0.0074 | 0.0581 | 0.0244 |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ba51e9e3a3a7d8cedf8bb0ee3e1b2096b45fe72981ebedbce74e94e187ce18e
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5adc281476bdb5ff9a5b7c6e1577ae6ad66856906512562ba25161329e13f665
3
  size 290403936
runs/Mar11_15-23-41_1e4e0d7704d7/events.out.tfevents.1741706624.1e4e0d7704d7.23.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed0d3907919bef393e35195408a8e8c26b9f77336b8baae725cb9b3507dab9e2
3
- size 82657
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfd66ccb8352f6e3034771ca817172793e58e11a587246ea677483b6167c0de8
3
+ size 83011
runs/Mar11_15-23-41_1e4e0d7704d7/events.out.tfevents.1741731835.1e4e0d7704d7.23.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e476a1f1f8cedfaab49e40d04c7ec15b095b76faa31e586cdb196c0525a2ce1d
3
+ size 453