Hugging Face's logo

YoussefAshmawy
/
Graduation_Project_Whisper_base

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
arabic
quran
Eval Results (legacy)
Model card Files
xet
Metrics Community
YoussefAshmawy commited on
Commit
27d44cd
·
verified ·
1 Parent(s): 4a0162a

Training finished

Browse files
Files changed (4) hide show
  1. README.md +28 -28
  2. model.safetensors +1 -1
  3. runs/Dec31_02-47-41_68cd7102c891/events.out.tfevents.1735613264.68cd7102c891.23.0 +2 -2
  4. runs/Dec31_02-47-41_68cd7102c891/events.out.tfevents.1735649214.68cd7102c891.23.1 +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: 0.0067
24
- - Wer: 0.0780
25
- - Cer: 0.0308
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
- | 0.0035 | 0.9990 | 512 | 0.0064 | 0.0713 | 0.0269 |
61
- | 0.0036 | 2.0 | 1025 | 0.0079 | 0.0862 | 0.0344 |
62
- | 0.0024 | 2.9990 | 1537 | 0.0084 | 0.0852 | 0.0321 |
63
- | 0.0014 | 4.0 | 2050 | 0.0089 | 0.0887 | 0.0341 |
64
- | 0.0013 | 4.9990 | 2562 | 0.0104 | 0.0876 | 0.0336 |
65
- | 0.0008 | 6.0 | 3075 | 0.0104 | 0.0930 | 0.0357 |
66
- | 0.0013 | 6.9990 | 3587 | 0.0109 | 0.1008 | 0.0400 |
67
- | 0.0006 | 8.0 | 4100 | 0.0102 | 0.0851 | 0.0342 |
68
- | 0.0007 | 8.9990 | 4612 | 0.0107 | 0.0898 | 0.0350 |
69
- | 0.0004 | 10.0 | 5125 | 0.0111 | 0.0896 | 0.0342 |
70
- | 0.0004 | 10.9990 | 5637 | 0.0106 | 0.0847 | 0.0309 |
71
- | 0.0003 | 12.0 | 6150 | 0.0111 | 0.0845 | 0.0325 |
72
- | 0.0003 | 12.9990 | 6662 | 0.0116 | 0.0820 | 0.0307 |
73
- | 0.0004 | 14.0 | 7175 | 0.0120 | 0.0851 | 0.0315 |
74
- | 0.0001 | 14.9990 | 7687 | 0.0116 | 0.0840 | 0.0352 |
75
- | 0.0001 | 16.0 | 8200 | 0.0116 | 0.0847 | 0.0329 |
76
- | 0.0001 | 16.9990 | 8712 | 0.0116 | 0.0795 | 0.0331 |
77
- | 0.0 | 18.0 | 9225 | 0.0119 | 0.0813 | 0.0304 |
78
- | 0.0 | 18.9990 | 9737 | 0.0123 | 0.0843 | 0.0334 |
79
- | 0.0 | 20.0 | 10250 | 0.0124 | 0.0820 | 0.0317 |
80
- | 0.0 | 20.9990 | 10762 | 0.0129 | 0.0831 | 0.0315 |
81
- | 0.0 | 22.0 | 11275 | 0.0122 | 0.0833 | 0.0323 |
82
- | 0.0003 | 22.9990 | 11787 | 0.0120 | 0.0843 | 0.0335 |
83
- | 0.0 | 24.0 | 12300 | 0.0117 | 0.0777 | 0.0304 |
84
- | 0.0 | 24.9756 | 12800 | 0.0123 | 0.0818 | 0.0318 |
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: 0.0071
24
+ - Wer: 0.0806
25
+ - Cer: 0.0311
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
60
+ | 0.0102 | 0.9990 | 512 | 0.0070 | 0.0757 | 0.0272 |
61
+ | 0.0059 | 2.0 | 1025 | 0.0082 | 0.0903 | 0.0351 |
62
+ | 0.0014 | 2.9990 | 1537 | 0.0097 | 0.0941 | 0.0395 |
63
+ | 0.0013 | 4.0 | 2050 | 0.0091 | 0.0827 | 0.0295 |
64
+ | 0.0015 | 4.9990 | 2562 | 0.0097 | 0.0909 | 0.0345 |
65
+ | 0.001 | 6.0 | 3075 | 0.0096 | 0.0883 | 0.0309 |
66
+ | 0.0007 | 6.9990 | 3587 | 0.0108 | 0.0820 | 0.0326 |
67
+ | 0.0007 | 8.0 | 4100 | 0.0099 | 0.0843 | 0.0331 |
68
+ | 0.0008 | 8.9990 | 4612 | 0.0109 | 0.0822 | 0.0315 |
69
+ | 0.0005 | 10.0 | 5125 | 0.0118 | 0.0874 | 0.0331 |
70
+ | 0.0003 | 10.9990 | 5637 | 0.0113 | 0.0854 | 0.0320 |
71
+ | 0.0003 | 12.0 | 6150 | 0.0109 | 0.0860 | 0.0333 |
72
+ | 0.0005 | 12.9990 | 6662 | 0.0109 | 0.0824 | 0.0337 |
73
+ | 0.0001 | 14.0 | 7175 | 0.0116 | 0.0822 | 0.0310 |
74
+ | 0.0001 | 14.9990 | 7687 | 0.0116 | 0.0787 | 0.0304 |
75
+ | 0.0001 | 16.0 | 8200 | 0.0119 | 0.0786 | 0.0302 |
76
+ | 0.0002 | 16.9990 | 8712 | 0.0117 | 0.0782 | 0.0306 |
77
+ | 0.0 | 18.0 | 9225 | 0.0117 | 0.0789 | 0.0307 |
78
+ | 0.0 | 18.9990 | 9737 | 0.0119 | 0.0789 | 0.0283 |
79
+ | 0.0001 | 20.0 | 10250 | 0.0120 | 0.0798 | 0.0316 |
80
+ | 0.0 | 20.9990 | 10762 | 0.0121 | 0.0762 | 0.0304 |
81
+ | 0.0 | 22.0 | 11275 | 0.0125 | 0.0789 | 0.0302 |
82
+ | 0.0 | 22.9990 | 11787 | 0.0126 | 0.0775 | 0.0310 |
83
+ | 0.0 | 24.0 | 12300 | 0.0122 | 0.0772 | 0.0322 |
84
+ | 0.0 | 24.9756 | 12800 | 0.0127 | 0.0778 | 0.0303 |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb5e5bd12d546ac336e6abc3dd297a8b9e2d510b8b3e0c7a695d3c99342591ca
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df20c841f8d8ab54e3a6cc1a52ebb64e3867db3593cfba04cbcadac8153f8123
3
  size 290403936
runs/Dec31_02-47-41_68cd7102c891/events.out.tfevents.1735613264.68cd7102c891.23.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06c6ef7b2e1af770f8671001b5b111e7cee83ed57e045a00b1ec2e0116ba0f3c
3
- size 123169
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46f61f2bebc7e399e63a1afeaf2d71629b628c110c4cffd784e89ef3cf69338e
3
+ size 123523
runs/Dec31_02-47-41_68cd7102c891/events.out.tfevents.1735649214.68cd7102c891.23.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bac324fc376304af2bb42759b10db8cefd04284d393a16f9cf2422e331133efa
3
+ size 453