Hugging Face's logo

Baselhany
/
Graduation_Project_Whisper_tiny_fine_tune_Quran

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
Baselhany commited on
Commit
17046bb
·
verified ·
1 Parent(s): 36df58b

Training finished

Browse files
Files changed (2) hide show
  1. README.md +18 -18
  2. runs/Feb20_00-11-50_9785e15e2ec6/events.out.tfevents.1740036256.9785e15e2ec6.18.1 +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-tiny](https://huggingface.co/openai/whisper-tiny) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0295
24
- - Wer: 18.2294
25
- - Cer: 5.7631
26
 
27
  ## Model description
28
 
@@ -57,21 +57,21 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-------:|:----:|:---------------:|:-------:|:------:|
60
- | 0.01 | 1.0 | 157 | 0.0199 | 19.8029 | 6.3519 |
61
- | 0.0055 | 2.0 | 314 | 0.0211 | 20.8552 | 6.9799 |
62
- | 0.0036 | 3.0 | 471 | 0.0257 | 21.6265 | 7.0476 |
63
- | 0.0033 | 4.0 | 628 | 0.0259 | 22.0074 | 7.2900 |
64
- | 0.0026 | 5.0 | 785 | 0.0277 | 21.6265 | 7.7954 |
65
- | 0.0019 | 6.0 | 942 | 0.0297 | 21.4122 | 7.2057 |
66
- | 0.0014 | 7.0 | 1099 | 0.0271 | 20.3695 | 6.4618 |
67
- | 0.0009 | 8.0 | 1256 | 0.0295 | 19.7981 | 6.5333 |
68
- | 0.0006 | 9.0 | 1413 | 0.0283 | 18.8077 | 6.0707 |
69
- | 0.0003 | 10.0 | 1570 | 0.0283 | 18.8696 | 5.9392 |
70
- | 0.0001 | 11.0 | 1727 | 0.0280 | 18.8077 | 5.9087 |
71
- | 0.0 | 12.0 | 1884 | 0.0281 | 17.9126 | 5.5364 |
72
- | 0.0 | 13.0 | 2041 | 0.0284 | 17.2079 | 5.3184 |
73
- | 0.0 | 14.0 | 2198 | 0.0289 | 17.2031 | 5.3118 |
74
- | 0.0 | 14.9088 | 2340 | 0.0290 | 17.1269 | 5.2729 |
75
 
76
 
77
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0279
24
+ - Wer: 17.5785
25
+ - Cer: 5.6568
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-------:|:----:|:---------------:|:-------:|:------:|
60
+ | 0.0103 | 1.0 | 157 | 0.0183 | 18.2840 | 5.9614 |
61
+ | 0.0078 | 2.0 | 314 | 0.0190 | 19.0839 | 6.1522 |
62
+ | 0.0051 | 3.0 | 471 | 0.0246 | 20.9409 | 6.7430 |
63
+ | 0.0036 | 4.0 | 628 | 0.0246 | 21.5741 | 8.3374 |
64
+ | 0.0028 | 5.0 | 785 | 0.0253 | 22.0265 | 7.7333 |
65
+ | 0.002 | 6.0 | 942 | 0.0265 | 21.8313 | 7.0642 |
66
+ | 0.0014 | 7.0 | 1099 | 0.0263 | 21.2313 | 6.9527 |
67
+ | 0.001 | 8.0 | 1256 | 0.0278 | 20.2124 | 6.6088 |
68
+ | 0.0007 | 9.0 | 1413 | 0.0272 | 20.0552 | 6.6726 |
69
+ | 0.0003 | 10.0 | 1570 | 0.0276 | 19.5553 | 6.4368 |
70
+ | 0.0002 | 11.0 | 1727 | 0.0271 | 19.1886 | 6.3686 |
71
+ | 0.0 | 12.0 | 1884 | 0.0277 | 18.1840 | 5.8188 |
72
+ | 0.0 | 13.0 | 2041 | 0.0278 | 18.0792 | 5.7983 |
73
+ | 0.0 | 14.0 | 2198 | 0.0284 | 17.7126 | 5.6308 |
74
+ | 0.0 | 14.9088 | 2340 | 0.0285 | 17.6031 | 5.5991 |
75
 
76
 
77
  ### Framework versions
runs/Feb20_00-11-50_9785e15e2ec6/events.out.tfevents.1740036256.9785e15e2ec6.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:111e771aa2a117ac2c449d6e723adde893f317f8c2c749196d2a4088f3587d61
3
+ size 453