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
6a9da95
·
verified ·
1 Parent(s): 118bb63

Training finished

Browse files
Files changed (3) hide show
  1. README.md +31 -58
  2. model.safetensors +1 -1
  3. runs/Dec16_14-44-29_c4da64f94285/events.out.tfevents.1734368789.c4da64f94285.23.1 +3 -0
README.md CHANGED
@@ -20,8 +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: 0.0479
24
- - Wer: 0.2408
 
25
 
26
  ## Model description
27
 
@@ -42,7 +43,7 @@ More information needed
42
  The following hyperparameters were used during training:
43
  - learning_rate: 0.0001
44
  - train_batch_size: 8
45
- - eval_batch_size: 4
46
  - seed: 42
47
  - gradient_accumulation_steps: 2
48
  - total_train_batch_size: 16
@@ -54,61 +55,33 @@ The following hyperparameters were used during training:
54
 
55
  ### Training results
56
 
57
- | Training Loss | Epoch | Step | Validation Loss | Wer |
58
- |:-------------:|:-------:|:----:|:---------------:|:------:|
59
- | 0.0498 | 0.4651 | 100 | 0.0378 | 0.3465 |
60
- | 0.0397 | 0.9302 | 200 | 0.0313 | 0.2965 |
61
- | 0.0235 | 1.3953 | 300 | 0.0323 | 0.2712 |
62
- | 0.0342 | 1.8605 | 400 | 0.0337 | 0.2919 |
63
- | 0.0151 | 2.3256 | 500 | 0.0428 | 0.2779 |
64
- | 0.0206 | 2.7907 | 600 | 0.0382 | 0.3221 |
65
- | 0.0115 | 3.2558 | 700 | 0.0414 | 0.3213 |
66
- | 0.0126 | 3.7209 | 800 | 0.0435 | 0.3636 |
67
- | 0.0075 | 4.1860 | 900 | 0.0425 | 0.2909 |
68
- | 0.0071 | 4.6512 | 1000 | 0.0439 | 0.3039 |
69
- | 0.0049 | 5.1163 | 1100 | 0.0442 | 0.2731 |
70
- | 0.0047 | 5.5814 | 1200 | 0.0443 | 0.3161 |
71
- | 0.0047 | 6.0465 | 1300 | 0.0452 | 0.2933 |
72
- | 0.0027 | 6.5116 | 1400 | 0.0459 | 0.2898 |
73
- | 0.004 | 6.9767 | 1500 | 0.0456 | 0.2771 |
74
- | 0.0017 | 7.4419 | 1600 | 0.0463 | 0.2482 |
75
- | 0.0018 | 7.9070 | 1700 | 0.0458 | 0.2818 |
76
- | 0.0016 | 8.3721 | 1800 | 0.0464 | 0.2523 |
77
- | 0.0014 | 8.8372 | 1900 | 0.0460 | 0.2621 |
78
- | 0.0012 | 9.3023 | 2000 | 0.0474 | 0.2606 |
79
- | 0.0009 | 9.7674 | 2100 | 0.0473 | 0.2575 |
80
- | 0.0008 | 10.2326 | 2200 | 0.0479 | 0.2723 |
81
- | 0.0008 | 10.6977 | 2300 | 0.0469 | 0.2710 |
82
- | 0.0007 | 11.1628 | 2400 | 0.0488 | 0.2773 |
83
- | 0.0008 | 11.6279 | 2500 | 0.0481 | 0.2507 |
84
- | 0.0006 | 12.0930 | 2600 | 0.0481 | 0.2632 |
85
- | 0.0007 | 12.5581 | 2700 | 0.0496 | 0.2586 |
86
- | 0.0003 | 13.0233 | 2800 | 0.0477 | 0.2646 |
87
- | 0.0003 | 13.4884 | 2900 | 0.0484 | 0.2455 |
88
- | 0.0003 | 13.9535 | 3000 | 0.0476 | 0.2496 |
89
- | 0.0003 | 14.4186 | 3100 | 0.0485 | 0.2487 |
90
- | 0.0001 | 14.8837 | 3200 | 0.0483 | 0.2474 |
91
- | 0.0002 | 15.3488 | 3300 | 0.0484 | 0.2468 |
92
- | 0.0002 | 15.8140 | 3400 | 0.0484 | 0.2469 |
93
- | 0.0001 | 16.2791 | 3500 | 0.0485 | 0.2448 |
94
- | 0.0 | 16.7442 | 3600 | 0.0479 | 0.2408 |
95
- | 0.0001 | 17.2093 | 3700 | 0.0481 | 0.2554 |
96
- | 0.0 | 17.6744 | 3800 | 0.0482 | 0.2505 |
97
- | 0.0 | 18.1395 | 3900 | 0.0482 | 0.2501 |
98
- | 0.0 | 18.6047 | 4000 | 0.0483 | 0.2480 |
99
- | 0.0 | 19.0698 | 4100 | 0.0484 | 0.2431 |
100
- | 0.0 | 19.5349 | 4200 | 0.0485 | 0.2470 |
101
- | 0.0 | 20.0 | 4300 | 0.0486 | 0.2447 |
102
- | 0.0 | 20.4651 | 4400 | 0.0486 | 0.2461 |
103
- | 0.0 | 20.9302 | 4500 | 0.0487 | 0.2539 |
104
- | 0.0 | 21.3953 | 4600 | 0.0488 | 0.2482 |
105
- | 0.0 | 21.8605 | 4700 | 0.0488 | 0.2505 |
106
- | 0.0 | 22.3256 | 4800 | 0.0488 | 0.2482 |
107
- | 0.0 | 22.7907 | 4900 | 0.0489 | 0.2487 |
108
- | 0.0 | 23.2558 | 5000 | 0.0489 | 0.2494 |
109
- | 0.0 | 23.7209 | 5100 | 0.0489 | 0.2525 |
110
- | 0.0 | 24.1860 | 5200 | 0.0489 | 0.2479 |
111
- | 0.0 | 24.6512 | 5300 | 0.0490 | 0.2440 |
112
 
113
 
114
  ### 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: 0.0712
24
+ - Wer: 0.2734
25
+ - Cer: 0.1522
26
 
27
  ## Model description
28
 
 
43
  The following hyperparameters were used during training:
44
  - learning_rate: 0.0001
45
  - train_batch_size: 8
46
+ - eval_batch_size: 8
47
  - seed: 42
48
  - gradient_accumulation_steps: 2
49
  - total_train_batch_size: 16
 
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
+ |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
60
+ | 0.0 | 0.9841 | 31 | 0.0708 | 0.2633 | 0.1470 |
61
+ | 0.0 | 2.0 | 63 | 0.0711 | 0.2659 | 0.1491 |
62
+ | 0.0 | 2.9841 | 94 | 0.0715 | 0.2710 | 0.1534 |
63
+ | 0.0 | 4.0 | 126 | 0.0720 | 0.2638 | 0.1460 |
64
+ | 0.0 | 4.9841 | 157 | 0.0725 | 0.2705 | 0.1505 |
65
+ | 0.0 | 6.0 | 189 | 0.0731 | 0.2968 | 0.1687 |
66
+ | 0.0 | 6.9841 | 220 | 0.0736 | 0.2856 | 0.1595 |
67
+ | 0.0 | 8.0 | 252 | 0.0741 | 0.2870 | 0.1604 |
68
+ | 0.0 | 8.9841 | 283 | 0.0745 | 0.2708 | 0.1485 |
69
+ | 0.0 | 10.0 | 315 | 0.0750 | 0.2717 | 0.1500 |
70
+ | 0.0 | 10.9841 | 346 | 0.0755 | 0.2777 | 0.1566 |
71
+ | 0.0 | 12.0 | 378 | 0.0759 | 0.2777 | 0.1579 |
72
+ | 0.0 | 12.9841 | 409 | 0.0763 | 0.2733 | 0.1534 |
73
+ | 0.0 | 14.0 | 441 | 0.0766 | 0.2691 | 0.1504 |
74
+ | 0.0 | 14.9841 | 472 | 0.0769 | 0.2831 | 0.1629 |
75
+ | 0.0 | 16.0 | 504 | 0.0773 | 0.2738 | 0.1512 |
76
+ | 0.0 | 16.9841 | 535 | 0.0776 | 0.2868 | 0.1643 |
77
+ | 0.0 | 18.0 | 567 | 0.0778 | 0.2798 | 0.1574 |
78
+ | 0.0 | 18.9841 | 598 | 0.0780 | 0.2763 | 0.1520 |
79
+ | 0.0 | 20.0 | 630 | 0.0781 | 0.2701 | 0.1483 |
80
+ | 0.0 | 20.9841 | 661 | 0.0782 | 0.2814 | 0.1574 |
81
+ | 0.0 | 22.0 | 693 | 0.0783 | 0.2768 | 0.1539 |
82
+ | 0.0 | 22.9841 | 724 | 0.0784 | 0.2705 | 0.1490 |
83
+ | 0.0 | 24.0 | 756 | 0.0788 | 0.2774 | 0.1563 |
84
+ | 0.0 | 24.6032 | 775 | 0.0784 | 0.2770 | 0.1550 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d9d013a7c580e2dabcde152a3a47a864593773c61c9344f0f95e70939b4919a
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3182eb15b6adc6f5aa65e0b515e74ad619cd60c5a515d2908868c992e9efbc5
3
  size 290403936
runs/Dec16_14-44-29_c4da64f94285/events.out.tfevents.1734368789.c4da64f94285.23.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34862261ccc0fadcda109176c786c2708df8a08211252e6d96e6c627e1382557
3
+ size 453