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
4aba392
·
verified ·
1 Parent(s): eea76d5

Training finished

Browse files
Files changed (3) hide show
  1. README.md +31 -33
  2. model.safetensors +1 -1
  3. runs/Dec28_01-37-08_f828e42bcbde/events.out.tfevents.1735383373.f828e42bcbde.23.1 +3 -0
README.md CHANGED
@@ -8,11 +8,9 @@ tags:
8
  - generated_from_trainer
9
  metrics:
10
  - wer
11
- - cer
12
  model-index:
13
  - name: Whisper base AR - YA
14
  results: []
15
- pipeline_tag: automatic-speech-recognition
16
  ---
17
 
18
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -22,9 +20,9 @@ should probably proofread and complete it, then remove this comment. -->
22
 
23
  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.
24
  It achieves the following results on the evaluation set:
25
- - Loss: 0.0167
26
- - Wer: 0.0944
27
- - Cer: 0.0360
28
 
29
  ## Model description
30
 
@@ -57,33 +55,33 @@ The following hyperparameters were used during training:
57
 
58
  ### Training results
59
 
60
- | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
61
- |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
62
- | 0.0081 | 1.0 | 375 | 0.0090 | 0.0947 | 0.0349 |
63
- | 0.0037 | 2.0 | 750 | 0.0124 | 0.1249 | 0.0467 |
64
- | 0.0027 | 3.0 | 1125 | 0.0125 | 0.1238 | 0.0484 |
65
- | 0.0019 | 4.0 | 1500 | 0.0130 | 0.1135 | 0.0414 |
66
- | 0.0012 | 5.0 | 1875 | 0.0130 | 0.1077 | 0.0375 |
67
- | 0.0009 | 6.0 | 2250 | 0.0128 | 0.1081 | 0.0406 |
68
- | 0.0008 | 7.0 | 2625 | 0.0153 | 0.1184 | 0.0396 |
69
- | 0.0009 | 8.0 | 3000 | 0.0149 | 0.1066 | 0.0371 |
70
- | 0.0004 | 9.0 | 3375 | 0.0147 | 0.0992 | 0.0347 |
71
- | 0.0006 | 10.0 | 3750 | 0.0149 | 0.1093 | 0.0396 |
72
- | 0.0014 | 11.0 | 4125 | 0.0146 | 0.1071 | 0.0390 |
73
- | 0.0005 | 12.0 | 4500 | 0.0142 | 0.1014 | 0.0370 |
74
- | 0.0007 | 13.0 | 4875 | 0.0162 | 0.1131 | 0.0410 |
75
- | 0.0005 | 14.0 | 5250 | 0.0148 | 0.0999 | 0.0361 |
76
- | 0.0002 | 15.0 | 5625 | 0.0152 | 0.1019 | 0.0400 |
77
- | 0.0 | 16.0 | 6000 | 0.0154 | 0.0948 | 0.0332 |
78
- | 0.0 | 17.0 | 6375 | 0.0156 | 0.0910 | 0.0330 |
79
- | 0.0 | 18.0 | 6750 | 0.0164 | 0.1003 | 0.0373 |
80
- | 0.0 | 19.0 | 7125 | 0.0156 | 0.0927 | 0.0319 |
81
- | 0.0001 | 20.0 | 7500 | 0.0158 | 0.0905 | 0.0314 |
82
- | 0.0 | 21.0 | 7875 | 0.0159 | 0.0918 | 0.0324 |
83
- | 0.0 | 22.0 | 8250 | 0.0158 | 0.0890 | 0.0315 |
84
- | 0.0 | 23.0 | 8625 | 0.0159 | 0.0892 | 0.0317 |
85
- | 0.0 | 24.0 | 9000 | 0.0167 | 0.0942 | 0.0357 |
86
- | 0.0 | 25.0 | 9375 | 0.0160 | 0.0885 | 0.0308 |
87
 
88
 
89
  ### Framework versions
@@ -91,4 +89,4 @@ The following hyperparameters were used during training:
91
  - Transformers 4.46.3
92
  - Pytorch 2.4.0
93
  - Datasets 3.1.0
94
- - Tokenizers 0.20.3
 
8
  - generated_from_trainer
9
  metrics:
10
  - wer
 
11
  model-index:
12
  - name: Whisper base AR - YA
13
  results: []
 
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
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: 0.0152
24
+ - Wer: 0.0879
25
+ - Cer: 0.0347
26
 
27
  ## Model description
28
 
 
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
60
+ | 0.0047 | 1.0 | 469 | 0.0091 | 0.0872 | 0.0328 |
61
+ | 0.0048 | 2.0 | 938 | 0.0112 | 0.1021 | 0.0394 |
62
+ | 0.0025 | 3.0 | 1407 | 0.0119 | 0.1030 | 0.0388 |
63
+ | 0.0018 | 4.0 | 1876 | 0.0125 | 0.1104 | 0.0449 |
64
+ | 0.0015 | 5.0 | 2345 | 0.0124 | 0.1015 | 0.0379 |
65
+ | 0.0014 | 6.0 | 2814 | 0.0131 | 0.1019 | 0.0379 |
66
+ | 0.0012 | 7.0 | 3283 | 0.0129 | 0.1059 | 0.0407 |
67
+ | 0.001 | 8.0 | 3752 | 0.0134 | 0.1053 | 0.0381 |
68
+ | 0.0005 | 9.0 | 4221 | 0.0131 | 0.0912 | 0.0350 |
69
+ | 0.0004 | 10.0 | 4690 | 0.0137 | 0.0948 | 0.0351 |
70
+ | 0.0006 | 11.0 | 5159 | 0.0136 | 0.1106 | 0.0393 |
71
+ | 0.0008 | 12.0 | 5628 | 0.0131 | 0.1023 | 0.0389 |
72
+ | 0.0004 | 13.0 | 6097 | 0.0137 | 0.0914 | 0.0343 |
73
+ | 0.0002 | 14.0 | 6566 | 0.0139 | 0.0956 | 0.0345 |
74
+ | 0.0002 | 15.0 | 7035 | 0.0138 | 0.0921 | 0.0342 |
75
+ | 0.0001 | 16.0 | 7504 | 0.0129 | 0.0843 | 0.0295 |
76
+ | 0.0 | 17.0 | 7973 | 0.0134 | 0.0860 | 0.0303 |
77
+ | 0.0 | 18.0 | 8442 | 0.0136 | 0.0834 | 0.0309 |
78
+ | 0.0 | 19.0 | 8911 | 0.0135 | 0.0838 | 0.0308 |
79
+ | 0.0 | 20.0 | 9380 | 0.0137 | 0.0887 | 0.0319 |
80
+ | 0.0 | 21.0 | 9849 | 0.0141 | 0.0833 | 0.0310 |
81
+ | 0.0 | 22.0 | 10318 | 0.0139 | 0.0829 | 0.0310 |
82
+ | 0.0 | 23.0 | 10787 | 0.0140 | 0.0852 | 0.0318 |
83
+ | 0.0 | 24.0 | 11256 | 0.0154 | 0.0873 | 0.0343 |
84
+ | 0.0 | 25.0 | 11725 | 0.0141 | 0.0840 | 0.0320 |
85
 
86
 
87
  ### Framework versions
 
89
  - Transformers 4.46.3
90
  - Pytorch 2.4.0
91
  - Datasets 3.1.0
92
+ - Tokenizers 0.20.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a33d3212efedc9bfe5624fdc4253045576cbb11b35160c752199d3e5f1937965
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb7a9d61d386582718bd5e11ebe235fa68c236b7bc37b6daeb01ad30f0cdfdbb
3
  size 290403936
runs/Dec28_01-37-08_f828e42bcbde/events.out.tfevents.1735383373.f828e42bcbde.23.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92a41ff6e2c79ac1fd073656497227a790a38bb4d765267ebf7bccdb617fa2d5
3
+ size 453