Downloads · 30 days
4
7% of all-time downloads
whisper-small-tr-v3
volkan-aslan/whisper-small-tr-v3
whisper-small-tr-v3 is a automatic speech recognition model from volkan-aslan. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
58
Public
Parameters
242M
9.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jun 7, 2025
- Updated
- Jun 8, 2025
- SHA
- c4424a40
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
Whisper Small TR V3 - Volkan ASLAN
This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3683
- Wer: 21.5362
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3.75e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- training_steps: 10000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2527 | 0.6894 | 1000 | 0.3620 | 28.3522 |
| 0.1164 | 1.3785 | 2000 | 0.3459 | 26.2727 |
| 0.0625 | 2.0676 | 3000 | 0.3380 | 25.2712 |
| 0.0642 | 2.7570 | 4000 | 0.3373 | 24.5218 |
| 0.0331 | 3.4461 | 5000 | 0.3440 | 23.9973 |
| 0.0133 | 4.1351 | 6000 | 0.3445 | 22.7795 |
| 0.0116 | 4.8245 | 7000 | 0.3537 | 22.8306 |
| 0.0041 | 5.5136 | 8000 | 0.3623 | 22.4202 |
| 0.002 | 6.2027 | 9000 | 0.3632 | 21.7355 |
| 0.0016 | 6.8921 | 10000 | 0.3683 | 21.5362 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.5.1+cu121
- Datasets 3.5.1
- Tokenizers 0.21.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- tr
- Created
- Jun 7, 2025
- Updated
- Jun 8, 2025