Hugging Face's logo

Baselhany
/
Graduation_Project_Whisper_tiny3

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
Baselhany commited on
Commit
703e4a3
·
verified ·
1 Parent(s): c978201

Training finished

Browse files
Files changed (3) hide show
  1. README.md +23 -23
  2. model.safetensors +1 -1
  3. runs/Feb04_00-09-26_9ae01280c1fd/events.out.tfevents.1738652735.9ae01280c1fd.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: 0.0244
24
- - Wer: 0.1485
25
- - Cer: 0.0491
26
 
27
  ## Model description
28
 
@@ -57,26 +57,26 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
60
- | 0.0508 | 1.0 | 157 | 0.0447 | 2.1609 | 0.9033 |
61
- | 0.0294 | 2.0 | 314 | 0.0286 | 1.9660 | 1.0025 |
62
- | 0.0226 | 3.0 | 471 | 0.0254 | 0.4391 | 0.1838 |
63
- | 0.0147 | 4.0 | 628 | 0.0224 | 0.3542 | 0.1358 |
64
- | 0.0129 | 5.0 | 785 | 0.0213 | 0.5243 | 0.2350 |
65
- | 0.0091 | 6.0 | 942 | 0.0199 | 0.3001 | 0.1045 |
66
- | 0.0065 | 7.0 | 1099 | 0.0196 | 0.2268 | 0.0728 |
67
- | 0.0043 | 8.0 | 1256 | 0.0196 | 0.2011 | 0.0645 |
68
- | 0.003 | 9.0 | 1413 | 0.0201 | 0.2885 | 0.1164 |
69
- | 0.003 | 10.0 | 1570 | 0.0209 | 0.3251 | 0.1150 |
70
- | 0.0016 | 11.0 | 1727 | 0.0207 | 0.1828 | 0.0607 |
71
- | 0.0009 | 12.0 | 1884 | 0.0209 | 0.1747 | 0.0537 |
72
- | 0.0007 | 13.0 | 2041 | 0.0211 | 0.1680 | 0.0517 |
73
- | 0.0005 | 14.0 | 2198 | 0.0218 | 0.1652 | 0.0504 |
74
- | 0.0003 | 15.0 | 2355 | 0.0211 | 0.1580 | 0.0496 |
75
- | 0.0002 | 16.0 | 2512 | 0.0216 | 0.1566 | 0.0487 |
76
- | 0.0001 | 17.0 | 2669 | 0.0224 | 0.1562 | 0.0492 |
77
- | 0.0 | 18.0 | 2826 | 0.0227 | 0.1481 | 0.0454 |
78
- | 0.0 | 19.0 | 2983 | 0.0239 | 0.1471 | 0.0489 |
79
- | 0.0 | 19.8768 | 3120 | 0.0237 | 0.1461 | 0.0462 |
80
 
81
 
82
  ### 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: 0.0180
24
+ - Wer: 0.1110
25
+ - Cer: 0.0427
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
60
+ | 0.0141 | 1.0 | 157 | 0.0135 | 0.1618 | 0.0599 |
61
+ | 0.0129 | 2.0 | 314 | 0.0135 | 0.1479 | 0.0451 |
62
+ | 0.0079 | 3.0 | 471 | 0.0161 | 0.1741 | 0.0609 |
63
+ | 0.0061 | 4.0 | 628 | 0.0159 | 0.1707 | 0.0537 |
64
+ | 0.0052 | 5.0 | 785 | 0.0162 | 0.1551 | 0.0519 |
65
+ | 0.0038 | 6.0 | 942 | 0.0166 | 0.1540 | 0.0520 |
66
+ | 0.0024 | 7.0 | 1099 | 0.0173 | 0.1332 | 0.0429 |
67
+ | 0.0019 | 8.0 | 1256 | 0.0171 | 0.1419 | 0.0446 |
68
+ | 0.0013 | 9.0 | 1413 | 0.0173 | 0.1455 | 0.0514 |
69
+ | 0.0011 | 10.0 | 1570 | 0.0170 | 0.1374 | 0.0453 |
70
+ | 0.0006 | 11.0 | 1727 | 0.0166 | 0.1292 | 0.0421 |
71
+ | 0.0004 | 12.0 | 1884 | 0.0170 | 0.1314 | 0.0415 |
72
+ | 0.0003 | 13.0 | 2041 | 0.0177 | 0.1274 | 0.0407 |
73
+ | 0.0003 | 14.0 | 2198 | 0.0171 | 0.1207 | 0.0381 |
74
+ | 0.0002 | 15.0 | 2355 | 0.0173 | 0.1240 | 0.0417 |
75
+ | 0.0001 | 16.0 | 2512 | 0.0175 | 0.1137 | 0.0362 |
76
+ | 0.0 | 17.0 | 2669 | 0.0171 | 0.1106 | 0.0378 |
77
+ | 0.0 | 18.0 | 2826 | 0.0172 | 0.1015 | 0.0341 |
78
+ | 0.0 | 19.0 | 2983 | 0.0183 | 0.1225 | 0.0464 |
79
+ | 0.0 | 19.8768 | 3120 | 0.0176 | 0.1821 | 0.0720 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d473c5eec1e55b56e54f82121d046e4c7aca2184b9197c850b0f31beda298699
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50db08d314cefaf1c457424b61350d7979d802c8457483274b6ff58bcc9f28dd
3
  size 151061672
runs/Feb04_00-09-26_9ae01280c1fd/events.out.tfevents.1738652735.9ae01280c1fd.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d388b87d45d6d880b2604f367ff15218183c13a424b972ce094dba3a601b8335
3
+ size 453