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
8d00671
·
verified ·
1 Parent(s): e903b5c

Training finished

Browse files
Files changed (3) hide show
  1. README.md +10 -21
  2. model.safetensors +1 -1
  3. runs/Jan21_11-04-12_82bc837fed48/events.out.tfevents.1737464656.82bc837fed48.18.1 +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: 0.0067
24
- - Wer: 0.0879
25
- - Cer: 0.0338
26
 
27
  ## Model description
28
 
@@ -50,28 +50,17 @@ The following hyperparameters were used during training:
50
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: linear
52
  - lr_scheduler_warmup_steps: 500
53
- - num_epochs: 15
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
- |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
60
- | 0.006 | 1.0 | 79 | 0.0066 | 0.0798 | 0.0302 |
61
- | 0.0081 | 2.0 | 158 | 0.0063 | 0.0793 | 0.0289 |
62
- | 0.0062 | 3.0 | 237 | 0.0062 | 0.0791 | 0.0294 |
63
- | 0.0047 | 4.0 | 316 | 0.0062 | 0.0824 | 0.0317 |
64
- | 0.0048 | 5.0 | 395 | 0.0063 | 0.0831 | 0.0312 |
65
- | 0.0036 | 6.0 | 474 | 0.0065 | 0.0824 | 0.0316 |
66
- | 0.0032 | 7.0 | 553 | 0.0067 | 0.0833 | 0.0324 |
67
- | 0.0022 | 8.0 | 632 | 0.0071 | 0.0825 | 0.0330 |
68
- | 0.0018 | 9.0 | 711 | 0.0076 | 0.0818 | 0.0318 |
69
- | 0.0007 | 10.0 | 790 | 0.0079 | 0.0827 | 0.0310 |
70
- | 0.001 | 11.0 | 869 | 0.0082 | 0.0860 | 0.0337 |
71
- | 0.0008 | 12.0 | 948 | 0.0084 | 0.0878 | 0.0330 |
72
- | 0.0006 | 13.0 | 1027 | 0.0085 | 0.0867 | 0.0336 |
73
- | 0.0003 | 14.0 | 1106 | 0.0093 | 0.0941 | 0.0400 |
74
- | 0.0005 | 14.8179 | 1170 | 0.0087 | 0.0894 | 0.0345 |
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: 0.0065
24
+ - Wer: 0.0838
25
+ - Cer: 0.0327
26
 
27
  ## Model description
28
 
 
50
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: linear
52
  - lr_scheduler_warmup_steps: 500
53
+ - num_epochs: 20
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
+ | 0.0065 | 1.0 | 235 | 0.0060 | 0.0766 | 0.0292 |
61
+ | 0.0071 | 2.0 | 470 | 0.0060 | 0.0802 | 0.0301 |
62
+ | 0.0067 | 3.0 | 705 | 0.0060 | 0.0767 | 0.0298 |
63
+ | 0.0041 | 4.0 | 940 | 0.0061 | 0.0814 | 0.0341 |
 
 
 
 
 
 
 
 
 
 
 
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64294708bbbc1cdfd7f44cb995283641ab3f931ebeed2de1c5c5cf9dfda69c0b
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:183b55edbf7c5029462a1a798285b8a9af6c9e275089a9bd4ff686e7ee300cf7
3
  size 151061672
runs/Jan21_11-04-12_82bc837fed48/events.out.tfevents.1737464656.82bc837fed48.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15d2b8bbea6de23ffc49e0f944f0662d63bd9a0cfcef7f9b5bdcf8ec4f503cb5
3
+ size 453