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
03d453e
·
verified ·
1 Parent(s): 787ac5c

Training finished

Browse files
Files changed (4) hide show
  1. README.md +28 -28
  2. model.safetensors +1 -1
  3. runs/Mar01_13-15-10_e2d071d07062/events.out.tfevents.1740834913.e2d071d07062.23.0 +2 -2
  4. runs/Mar01_13-15-10_e2d071d07062/events.out.tfevents.1740874135.e2d071d07062.23.1 +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: 0.0086
24
- - Wer: 0.0612
25
- - Cer: 0.0244
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
- | 0.0021 | 0.9991 | 562 | 0.0065 | 0.0827 | 0.0359 |
61
- | 0.001 | 2.0 | 1125 | 0.0072 | 0.0838 | 0.0306 |
62
- | 0.0013 | 2.9991 | 1687 | 0.0072 | 0.0791 | 0.0286 |
63
- | 0.0007 | 4.0 | 2250 | 0.0073 | 0.0773 | 0.0285 |
64
- | 0.0009 | 4.9991 | 2812 | 0.0079 | 0.0802 | 0.0323 |
65
- | 0.0003 | 6.0 | 3375 | 0.0086 | 0.0758 | 0.0289 |
66
- | 0.0006 | 6.9991 | 3937 | 0.0087 | 0.0905 | 0.0346 |
67
- | 0.0004 | 8.0 | 4500 | 0.0084 | 0.0724 | 0.0267 |
68
- | 0.0003 | 8.9991 | 5062 | 0.0082 | 0.0720 | 0.0264 |
69
- | 0.0003 | 10.0 | 5625 | 0.0081 | 0.0776 | 0.0300 |
70
- | 0.0002 | 10.9991 | 6187 | 0.0078 | 0.0681 | 0.0254 |
71
- | 0.0002 | 12.0 | 6750 | 0.0080 | 0.0671 | 0.0240 |
72
- | 0.0002 | 12.9991 | 7312 | 0.0084 | 0.0695 | 0.0273 |
73
- | 0.0001 | 14.0 | 7875 | 0.0083 | 0.0695 | 0.0264 |
74
- | 0.0001 | 14.9991 | 8437 | 0.0087 | 0.0728 | 0.0290 |
75
- | 0.0001 | 16.0 | 9000 | 0.0085 | 0.0675 | 0.0258 |
76
- | 0.0 | 16.9991 | 9562 | 0.0083 | 0.0652 | 0.0257 |
77
- | 0.0 | 18.0 | 10125 | 0.0083 | 0.0632 | 0.0248 |
78
- | 0.0 | 18.9991 | 10687 | 0.0088 | 0.0643 | 0.0256 |
79
- | 0.0 | 20.0 | 11250 | 0.0088 | 0.0617 | 0.0258 |
80
- | 0.0 | 20.9991 | 11812 | 0.0092 | 0.0632 | 0.0251 |
81
- | 0.0 | 22.0 | 12375 | 0.0092 | 0.0621 | 0.0251 |
82
- | 0.0 | 22.9991 | 12937 | 0.0093 | 0.0614 | 0.0246 |
83
- | 0.0 | 24.0 | 13500 | 0.0086 | 0.0615 | 0.0247 |
84
- | 0.0 | 24.9778 | 14050 | 0.0094 | 0.0605 | 0.0245 |
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: 0.0043
24
+ - Wer: 0.0607
25
+ - Cer: 0.0239
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
60
+ | 0.0044 | 0.9991 | 562 | 0.0046 | 0.0585 | 0.0235 |
61
+ | 0.0023 | 2.0 | 1125 | 0.0053 | 0.0724 | 0.0252 |
62
+ | 0.0011 | 2.9991 | 1687 | 0.0068 | 0.0690 | 0.0244 |
63
+ | 0.0008 | 4.0 | 2250 | 0.0071 | 0.0748 | 0.0268 |
64
+ | 0.0007 | 4.9991 | 2812 | 0.0070 | 0.0762 | 0.0271 |
65
+ | 0.0007 | 6.0 | 3375 | 0.0074 | 0.0729 | 0.0274 |
66
+ | 0.0007 | 6.9991 | 3937 | 0.0073 | 0.0791 | 0.0318 |
67
+ | 0.0005 | 8.0 | 4500 | 0.0071 | 0.0722 | 0.0255 |
68
+ | 0.0005 | 8.9991 | 5062 | 0.0076 | 0.0733 | 0.0276 |
69
+ | 0.0006 | 10.0 | 5625 | 0.0069 | 0.0677 | 0.0260 |
70
+ | 0.0003 | 10.9991 | 6187 | 0.0074 | 0.0644 | 0.0232 |
71
+ | 0.0002 | 12.0 | 6750 | 0.0077 | 0.0684 | 0.0247 |
72
+ | 0.0 | 12.9991 | 7312 | 0.0080 | 0.0633 | 0.0242 |
73
+ | 0.0002 | 14.0 | 7875 | 0.0082 | 0.0693 | 0.0256 |
74
+ | 0.0001 | 14.9991 | 8437 | 0.0081 | 0.0706 | 0.0263 |
75
+ | 0.0001 | 16.0 | 9000 | 0.0083 | 0.0677 | 0.0256 |
76
+ | 0.0001 | 16.9991 | 9562 | 0.0082 | 0.0643 | 0.0256 |
77
+ | 0.0 | 18.0 | 10125 | 0.0083 | 0.0661 | 0.0256 |
78
+ | 0.0 | 18.9991 | 10687 | 0.0084 | 0.0662 | 0.0261 |
79
+ | 0.0 | 20.0 | 11250 | 0.0083 | 0.0657 | 0.0274 |
80
+ | 0.0 | 20.9991 | 11812 | 0.0084 | 0.0670 | 0.0263 |
81
+ | 0.0 | 22.0 | 12375 | 0.0085 | 0.0635 | 0.0255 |
82
+ | 0.0 | 22.9991 | 12937 | 0.0085 | 0.0641 | 0.0256 |
83
+ | 0.0 | 24.0 | 13500 | 0.0081 | 0.0618 | 0.0253 |
84
+ | 0.0 | 24.9778 | 14050 | 0.0086 | 0.0615 | 0.0239 |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f0659b7ad0f803077bd0c1dbd355c430fa4af8f1ab60fe9ed0131f85985f796
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01a827e48db0e0de15608ff7b01022e9a271aaac40f2ec7110d44b32ff3ab05a
3
  size 290403936
runs/Mar01_13-15-10_e2d071d07062/events.out.tfevents.1740834913.e2d071d07062.23.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d08916c52068b8c1a8027658e3119a356af193c9efb6f159b5eeeb5321ca24c6
3
- size 133719
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4636c0cd979899b93d92fc3a0d9919893f153bc0a18aa74a60ac0bb6867fd26d
3
+ size 134073
runs/Mar01_13-15-10_e2d071d07062/events.out.tfevents.1740874135.e2d071d07062.23.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0459054106d2e8499d9dbe03c01c4e273bec8b237ae0a76451698cdaec1470e1
3
+ size 453