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
23e0f6f
·
verified ·
1 Parent(s): c19c915

Training finished

Browse files
Files changed (3) hide show
  1. README.md +16 -10
  2. model.safetensors +1 -1
  3. runs/Jan19_11-57-15_4f3365e5d96a/events.out.tfevents.1737306520.4f3365e5d96a.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: 0.0069
24
- - Wer: 0.0867
25
- - Cer: 0.0343
26
 
27
  ## Model description
28
 
@@ -45,8 +45,8 @@ The following hyperparameters were used during training:
45
  - train_batch_size: 16
46
  - eval_batch_size: 16
47
  - seed: 42
48
- - gradient_accumulation_steps: 2
49
- - total_train_batch_size: 32
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
@@ -57,11 +57,17 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
- | 0.0073 | 1.0 | 469 | 0.0072 | 0.0881 | 0.0345 |
61
- | 0.0079 | 2.0 | 938 | 0.0068 | 0.0791 | 0.0310 |
62
- | 0.0052 | 3.0 | 1407 | 0.0069 | 0.0845 | 0.0327 |
63
- | 0.0027 | 4.0 | 1876 | 0.0074 | 0.0847 | 0.0336 |
64
- | 0.0035 | 5.0 | 2345 | 0.0075 | 0.0820 | 0.0295 |
 
 
 
 
 
 
65
 
66
 
67
  ### 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: 0.0076
24
+ - Wer: 0.0861
25
+ - Cer: 0.0359
26
 
27
  ## Model description
28
 
 
45
  - train_batch_size: 16
46
  - eval_batch_size: 16
47
  - seed: 42
48
+ - gradient_accumulation_steps: 4
49
+ - total_train_batch_size: 64
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
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
+ | 0.008 | 1.0 | 235 | 0.0066 | 0.0804 | 0.0302 |
61
+ | 0.0062 | 2.0 | 470 | 0.0064 | 0.0793 | 0.0305 |
62
+ | 0.0066 | 3.0 | 705 | 0.0063 | 0.0753 | 0.0302 |
63
+ | 0.0038 | 4.0 | 940 | 0.0064 | 0.0767 | 0.0288 |
64
+ | 0.0037 | 5.0 | 1175 | 0.0067 | 0.0766 | 0.0296 |
65
+ | 0.0031 | 6.0 | 1410 | 0.0069 | 0.0751 | 0.0291 |
66
+ | 0.002 | 7.0 | 1645 | 0.0074 | 0.0809 | 0.0309 |
67
+ | 0.0013 | 8.0 | 1880 | 0.0077 | 0.0796 | 0.0297 |
68
+ | 0.0016 | 9.0 | 2115 | 0.0079 | 0.0796 | 0.0297 |
69
+ | 0.001 | 10.0 | 2350 | 0.0083 | 0.0795 | 0.0297 |
70
+ | 0.0005 | 11.0 | 2585 | 0.0085 | 0.0780 | 0.0290 |
71
 
72
 
73
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d47ffded7f2bfa09d112a9c42faee88b10633246e80ec8fe6b0e0884876069e
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1e7c0562d0a795956674f634e4a5f21b4bf5788855aa6d76c9f14556ef1f837
3
  size 151061672
runs/Jan19_11-57-15_4f3365e5d96a/events.out.tfevents.1737306520.4f3365e5d96a.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c623aff9d58f933383fbc95cfec810672bbf42d6e64bdba230316397c6718caf
3
+ size 453