Hugging Face's logo

Baselhany
/
Whisper_tiny_tring_large_sample_with_early_stop2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Baselhany commited on
Commit
e33f089
·
verified ·
1 Parent(s): 59bef01

Training finished

Browse files
Files changed (3) hide show
  1. README.md +13 -11
  2. model.safetensors +1 -1
  3. runs/Jan25_14-42-16_0fce40daf52c/events.out.tfevents.1737842823.0fce40daf52c.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: 0.0180
24
- - Wer: 2.0030
25
- - Cer: 1.0182
26
 
27
  ## Model description
28
 
@@ -50,20 +50,22 @@ 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: 10
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
- | 0.0211 | 1.0 | 469 | 0.0229 | 2.6548 | 1.3564 |
61
- | 0.0192 | 2.0 | 938 | 0.0209 | 2.1622 | 1.1267 |
62
- | 0.0149 | 3.0 | 1407 | 0.0193 | 1.3596 | 0.6720 |
63
- | 0.0145 | 4.0 | 1876 | 0.0182 | 1.1658 | 0.6142 |
64
- | 0.0106 | 5.0 | 2345 | 0.0176 | 1.7265 | 0.9079 |
65
- | 0.0121 | 6.0 | 2814 | 0.0171 | 1.5142 | 0.7794 |
66
- | 0.0139 | 7.0 | 3283 | 0.0168 | 1.6885 | 0.8300 |
 
 
67
 
68
 
69
  ### 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: 0.0143
24
+ - Wer: 0.5006
25
+ - Cer: 0.2258
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: 15
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
+ | 0.019 | 1.0 | 469 | 0.0174 | 1.0592 | 0.5214 |
61
+ | 0.0145 | 2.0 | 938 | 0.0161 | 1.1772 | 0.5591 |
62
+ | 0.0149 | 3.0 | 1407 | 0.0153 | 0.6080 | 0.2749 |
63
+ | 0.0103 | 4.0 | 1876 | 0.0145 | 0.4434 | 0.1993 |
64
+ | 0.0092 | 5.0 | 2345 | 0.0141 | 0.4646 | 0.2128 |
65
+ | 0.0108 | 6.0 | 2814 | 0.0137 | 0.4534 | 0.2096 |
66
+ | 0.0084 | 7.0 | 3283 | 0.0135 | 0.4440 | 0.2115 |
67
+ | 0.0087 | 8.0 | 3752 | 0.0134 | 0.4793 | 0.2098 |
68
+ | 0.0074 | 9.0 | 4221 | 0.0134 | 0.4538 | 0.2090 |
69
 
70
 
71
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a2b64bb808938b179f4e327e23624c453d0947ad8e642dbd418ca56a4e7af75
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72eb34123b878d1e9cd0239a67936a002ed154ac6ed96474075bef6b229db4fa
3
  size 151061672
runs/Jan25_14-42-16_0fce40daf52c/events.out.tfevents.1737842823.0fce40daf52c.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b13cec972d942721238d69a7430e3058f5b3a726b028c24d8d0a1e76b55482
3
+ size 453