Hugging Face's logo

Baselhany
/
Graduation_Project_Whisper_tiny_fine_tune_Quran

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
Baselhany commited on
Commit
7927469
·
verified ·
1 Parent(s): 6d236f1

Training finished

Browse files
Files changed (3) hide show
  1. README.md +25 -25
  2. model.safetensors +1 -1
  3. runs/Feb18_02-28-56_b16e77a1b8c1/events.out.tfevents.1739881484.b16e77a1b8c1.18.1 +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: 0.0438
24
- - Wer: 32.5017
25
- - Cer: 11.2863
26
 
27
  ## Model description
28
 
@@ -55,28 +55,28 @@ The following hyperparameters were used during training:
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
- |:-------------:|:-------:|:----:|:---------------:|:--------:|:-------:|
60
- | 0.0908 | 1.0 | 157 | 0.0487 | 133.7254 | 51.6276 |
61
- | 0.0559 | 2.0 | 314 | 0.0376 | 116.8079 | 56.4424 |
62
- | 0.0399 | 3.0 | 471 | 0.0360 | 72.3741 | 29.9440 |
63
- | 0.0322 | 4.0 | 628 | 0.0331 | 46.4670 | 18.3025 |
64
- | 0.0238 | 5.0 | 785 | 0.0327 | 69.1553 | 33.0778 |
65
- | 0.0187 | 6.0 | 942 | 0.0345 | 51.3856 | 21.4801 |
66
- | 0.0125 | 7.0 | 1099 | 0.0334 | 35.0252 | 12.5225 |
67
- | 0.0085 | 8.0 | 1256 | 0.0353 | 44.2386 | 17.3333 |
68
- | 0.0054 | 9.0 | 1413 | 0.0377 | 32.1446 | 11.1328 |
69
- | 0.0031 | 10.0 | 1570 | 0.0382 | 44.5481 | 16.9993 |
70
- | 0.0022 | 11.0 | 1727 | 0.0397 | 37.7869 | 13.6092 |
71
- | 0.0012 | 12.0 | 1884 | 0.0413 | 35.0205 | 12.3760 |
72
- | 0.0008 | 13.0 | 2041 | 0.0406 | 33.5159 | 13.0772 |
73
- | 0.0005 | 14.0 | 2198 | 0.0427 | 33.9444 | 12.6318 |
74
- | 0.0002 | 15.0 | 2355 | 0.0431 | 31.4494 | 10.5670 |
75
- | 0.0001 | 16.0 | 2512 | 0.0439 | 35.3728 | 12.5241 |
76
- | 0.0 | 17.0 | 2669 | 0.0450 | 29.2686 | 10.1071 |
77
- | 0.0 | 18.0 | 2826 | 0.0467 | 30.4590 | 11.2831 |
78
- | 0.0 | 19.0 | 2983 | 0.0474 | 30.3352 | 11.1267 |
79
- | 0.0 | 19.8768 | 3120 | 0.0476 | 30.3781 | 11.1794 |
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: 0.0325
24
+ - Wer: 20.8702
25
+ - Cer: 6.5270
26
 
27
  ## Model description
28
 
 
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
+ |:-------------:|:-------:|:----:|:---------------:|:-------:|:-------:|
60
+ | 0.0195 | 1.0 | 157 | 0.0258 | 28.5306 | 9.6655 |
61
+ | 0.0126 | 2.0 | 314 | 0.0259 | 27.2307 | 9.0680 |
62
+ | 0.0094 | 3.0 | 471 | 0.0297 | 30.5114 | 10.1193 |
63
+ | 0.0082 | 4.0 | 628 | 0.0298 | 28.8877 | 9.5185 |
64
+ | 0.0057 | 5.0 | 785 | 0.0280 | 26.4499 | 8.9238 |
65
+ | 0.0042 | 6.0 | 942 | 0.0301 | 27.3498 | 8.5898 |
66
+ | 0.0029 | 7.0 | 1099 | 0.0288 | 25.1214 | 8.1566 |
67
+ | 0.0022 | 8.0 | 1256 | 0.0295 | 25.9261 | 8.3025 |
68
+ | 0.0017 | 9.0 | 1413 | 0.0302 | 24.9738 | 8.1305 |
69
+ | 0.0011 | 10.0 | 1570 | 0.0298 | 24.5310 | 7.9979 |
70
+ | 0.0009 | 11.0 | 1727 | 0.0316 | 24.4167 | 7.6839 |
71
+ | 0.0005 | 12.0 | 1884 | 0.0310 | 22.9645 | 7.4348 |
72
+ | 0.0003 | 13.0 | 2041 | 0.0311 | 22.6074 | 7.3300 |
73
+ | 0.0002 | 14.0 | 2198 | 0.0318 | 21.9741 | 6.9799 |
74
+ | 0.0001 | 15.0 | 2355 | 0.0309 | 21.4075 | 6.6726 |
75
+ | 0.0 | 16.0 | 2512 | 0.0312 | 20.8171 | 6.5150 |
76
+ | 0.0 | 17.0 | 2669 | 0.0318 | 20.8932 | 6.4546 |
77
+ | 0.0 | 18.0 | 2826 | 0.0324 | 20.6504 | 6.2743 |
78
+ | 0.0 | 19.0 | 2983 | 0.0329 | 20.4552 | 6.1739 |
79
+ | 0.0 | 19.8768 | 3120 | 0.0330 | 20.5171 | 6.2022 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c69e5eb690a9784d0e83e807cece62f6368aab7ae0707922e5eaf4a769db95a7
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c7035aebf193daae5bc51a733d759390e1220ae1a9ea26c3a30e739cbc7297a
3
  size 151061672
runs/Feb18_02-28-56_b16e77a1b8c1/events.out.tfevents.1739881484.b16e77a1b8c1.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6f2bd36baa6a53d00d655510fb7db30d4ec8066ac7967b9cf04eff0f0184340
3
+ size 453