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
59504bc
·
verified ·
1 Parent(s): 204bfd2

Training finished

Browse files
Files changed (3) hide show
  1. README.md +28 -28
  2. model.safetensors +1 -1
  3. runs/Dec17_09-00-44_e6376d6e74c1/events.out.tfevents.1734453532.e6376d6e74c1.23.1 +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: 0.0534
24
- - Wer: 0.2531
25
- - Cer: 0.1472
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
- | 0.0414 | 0.9968 | 156 | 0.0333 | 0.2962 | 0.1764 |
61
- | 0.0224 | 2.0 | 313 | 0.0308 | 0.2648 | 0.1568 |
62
- | 0.011 | 2.9968 | 469 | 0.0399 | 0.2968 | 0.1735 |
63
- | 0.0098 | 4.0 | 626 | 0.0433 | 0.3606 | 0.2108 |
64
- | 0.0077 | 4.9968 | 782 | 0.0448 | 0.3336 | 0.1946 |
65
- | 0.0046 | 6.0 | 939 | 0.0484 | 0.2924 | 0.1624 |
66
- | 0.0031 | 6.9968 | 1095 | 0.0469 | 0.2907 | 0.1607 |
67
- | 0.0013 | 8.0 | 1252 | 0.0463 | 0.2879 | 0.1635 |
68
- | 0.0008 | 8.9968 | 1408 | 0.0473 | 0.2663 | 0.1501 |
69
- | 0.0006 | 10.0 | 1565 | 0.0475 | 0.2666 | 0.1526 |
70
- | 0.0002 | 10.9968 | 1721 | 0.0475 | 0.2651 | 0.1537 |
71
- | 0.0001 | 12.0 | 1878 | 0.0479 | 0.2564 | 0.1507 |
72
- | 0.0 | 12.9968 | 2034 | 0.0480 | 0.2524 | 0.1459 |
73
- | 0.0001 | 14.0 | 2191 | 0.0487 | 0.2601 | 0.1534 |
74
- | 0.0 | 14.9968 | 2347 | 0.0488 | 0.2564 | 0.1454 |
75
- | 0.0 | 16.0 | 2504 | 0.0488 | 0.2541 | 0.1473 |
76
- | 0.0 | 16.9968 | 2660 | 0.0491 | 0.2496 | 0.1438 |
77
- | 0.0 | 18.0 | 2817 | 0.0492 | 0.2543 | 0.1471 |
78
- | 0.0 | 18.9968 | 2973 | 0.0493 | 0.2563 | 0.1489 |
79
- | 0.0 | 20.0 | 3130 | 0.0495 | 0.2476 | 0.1437 |
80
- | 0.0 | 20.9968 | 3286 | 0.0495 | 0.2480 | 0.1439 |
81
- | 0.0 | 22.0 | 3443 | 0.0496 | 0.2462 | 0.1420 |
82
- | 0.0 | 22.9968 | 3599 | 0.0497 | 0.2459 | 0.1415 |
83
- | 0.0 | 24.0 | 3756 | 0.0535 | 0.2542 | 0.1485 |
84
- | 0.0 | 24.9201 | 3900 | 0.0497 | 0.2476 | 0.1433 |
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: 0.0449
24
+ - Wer: 0.2335
25
+ - Cer: 0.1403
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
60
+ | 0.0325 | 0.9984 | 312 | 0.0272 | 0.2577 | 0.1518 |
61
+ | 0.02 | 2.0 | 625 | 0.0288 | 0.3105 | 0.2049 |
62
+ | 0.0142 | 2.9984 | 937 | 0.0324 | 0.2710 | 0.1628 |
63
+ | 0.0071 | 4.0 | 1250 | 0.0368 | 0.2844 | 0.1668 |
64
+ | 0.0044 | 4.9984 | 1562 | 0.0368 | 0.2965 | 0.1727 |
65
+ | 0.0033 | 6.0 | 1875 | 0.0394 | 0.2760 | 0.1565 |
66
+ | 0.0023 | 6.9984 | 2187 | 0.0396 | 0.2719 | 0.1605 |
67
+ | 0.0012 | 8.0 | 2500 | 0.0401 | 0.2679 | 0.1595 |
68
+ | 0.0011 | 8.9984 | 2812 | 0.0401 | 0.2401 | 0.1412 |
69
+ | 0.0012 | 10.0 | 3125 | 0.0415 | 0.2756 | 0.1711 |
70
+ | 0.0011 | 10.9984 | 3437 | 0.0411 | 0.2508 | 0.1440 |
71
+ | 0.0007 | 12.0 | 3750 | 0.0426 | 0.2658 | 0.1560 |
72
+ | 0.0008 | 12.9984 | 4062 | 0.0428 | 0.2548 | 0.1476 |
73
+ | 0.0007 | 14.0 | 4375 | 0.0436 | 0.2580 | 0.1531 |
74
+ | 0.0006 | 14.9984 | 4687 | 0.0447 | 0.2605 | 0.1478 |
75
+ | 0.0007 | 16.0 | 5000 | 0.0440 | 0.2602 | 0.1569 |
76
+ | 0.0002 | 16.9984 | 5312 | 0.0435 | 0.2443 | 0.1460 |
77
+ | 0.0001 | 18.0 | 5625 | 0.0443 | 0.2571 | 0.1515 |
78
+ | 0.0 | 18.9984 | 5937 | 0.0435 | 0.2482 | 0.1480 |
79
+ | 0.0 | 20.0 | 6250 | 0.0438 | 0.2440 | 0.1437 |
80
+ | 0.0 | 20.9984 | 6562 | 0.0438 | 0.2339 | 0.1371 |
81
+ | 0.0 | 22.0 | 6875 | 0.0438 | 0.2440 | 0.1465 |
82
+ | 0.0 | 22.9984 | 7187 | 0.0439 | 0.2513 | 0.1522 |
83
+ | 0.0 | 24.0 | 7500 | 0.0452 | 0.2363 | 0.1435 |
84
+ | 0.0 | 24.96 | 7800 | 0.0440 | 0.2440 | 0.1465 |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c801b9fea1e98b4549b23926823428c0635b675189fde2a0706c995004a6130e
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2939e5ce8bc2b1f004c84213b909d63715585ce269681eef695bd05a38b2af90
3
  size 290403936
runs/Dec17_09-00-44_e6376d6e74c1/events.out.tfevents.1734453532.e6376d6e74c1.23.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:255fc906f1f8d17e2572282eca877672a92a1bd53d4f72358c0db4d53be37b69
3
+ size 453