Hugging Face's logo

Baselhany
/
fine_tune_Whisper_tiny2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Baselhany commited on
Commit
2abdb34
·
verified ·
1 Parent(s): e4750f4

Training finished

Browse files
Files changed (3) hide show
  1. README.md +10 -20
  2. model.safetensors +1 -1
  3. runs/Jan18_16-48-02_5cd0164c7538/events.out.tfevents.1737228022.5cd0164c7538.18.1 +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: 0.0148
24
- - Wer: 0.1025
25
- - Cer: 0.0366
26
 
27
  ## Model description
28
 
@@ -57,23 +57,13 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
- | 0.0104 | 1.0 | 313 | 0.0092 | 0.1131 | 0.0389 |
61
- | 0.009 | 2.0 | 626 | 0.0091 | 0.1104 | 0.0405 |
62
- | 0.006 | 3.0 | 939 | 0.0093 | 0.1046 | 0.0371 |
63
- | 0.0056 | 4.0 | 1252 | 0.0097 | 0.1061 | 0.0369 |
64
- | 0.002 | 5.0 | 1565 | 0.0110 | 0.1061 | 0.0375 |
65
- | 0.0021 | 6.0 | 1878 | 0.0110 | 0.1052 | 0.0464 |
66
- | 0.0012 | 7.0 | 2191 | 0.0117 | 0.1019 | 0.0353 |
67
- | 0.0008 | 8.0 | 2504 | 0.0126 | 0.1071 | 0.0457 |
68
- | 0.0002 | 9.0 | 2817 | 0.0129 | 0.1019 | 0.0372 |
69
- | 0.0002 | 10.0 | 3130 | 0.0140 | 0.1056 | 0.0380 |
70
- | 0.0001 | 11.0 | 3443 | 0.0138 | 0.1003 | 0.0337 |
71
- | 0.0001 | 12.0 | 3756 | 0.0142 | 0.0977 | 0.0327 |
72
- | 0.0 | 13.0 | 4069 | 0.0146 | 0.1014 | 0.0346 |
73
- | 0.0 | 14.0 | 4382 | 0.0152 | 0.0988 | 0.0340 |
74
- | 0.0 | 15.0 | 4695 | 0.0164 | 0.1040 | 0.0390 |
75
- | 0.0 | 16.0 | 5008 | 0.0161 | 0.1005 | 0.0336 |
76
- | 0.0 | 17.0 | 5321 | 0.0165 | 0.1005 | 0.0330 |
77
 
78
 
79
  ### 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: 0.0099
24
+ - Wer: 0.1017
25
+ - Cer: 0.0375
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
+ | 0.0107 | 1.0 | 313 | 0.0098 | 0.1102 | 0.0433 |
61
+ | 0.0081 | 2.0 | 626 | 0.0087 | 0.1043 | 0.0376 |
62
+ | 0.0086 | 3.0 | 939 | 0.0092 | 0.0995 | 0.0346 |
63
+ | 0.0045 | 4.0 | 1252 | 0.0099 | 0.0994 | 0.0335 |
64
+ | 0.0023 | 5.0 | 1565 | 0.0108 | 0.1023 | 0.0394 |
65
+ | 0.001 | 6.0 | 1878 | 0.0117 | 0.1021 | 0.0353 |
66
+ | 0.0004 | 7.0 | 2191 | 0.0124 | 0.1012 | 0.0344 |
 
 
 
 
 
 
 
 
 
 
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7fb4c76d2a69fc8ded34978af424814d0581cf6f2cd10f004beaf6389c5a893b
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e309ba132e89845e20cde06a7134faee00af79588e36cc39f084d73c92204340
3
  size 151061672
runs/Jan18_16-48-02_5cd0164c7538/events.out.tfevents.1737228022.5cd0164c7538.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de77d36ddf6a99b09d47fb2e0b6b807f9aeced27c3371fa6f5bbe3fcdd42004d
3
+ size 453