Whisper Tiny TR
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 13 Turkish 70% dataset. It achieves the following results on the evaluation set:
- Loss: 0.5730
- Wer: 55.4805
Model description
More information needed
Todo
Train with mozilla-foundation/common_voice_13_0 after the initial training.
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3106 | 0.5 | 97 | 0.5626 | 57.0558 |
| 0.3361 | 1.0 | 194 | 0.5635 | 56.9995 |
| 0.3089 | 1.5 | 291 | 0.5639 | 57.6184 |
| 0.2665 | 1.99 | 388 | 0.5746 | 56.4088 |
| 0.2794 | 2.49 | 485 | 0.5799 | 56.2213 |
| 0.2364 | 2.99 | 582 | 0.5730 | 55.4805 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 11
Model tree for beratcmn/whisper-tiny-tr
Base model
openai/whisper-tiny