Whisper tiny tr - Pinar Savci
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5405
- Wer: 43.8474
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: 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
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4111 | 0.8857 | 1000 | 0.5962 | 47.4549 |
| 0.3035 | 1.7715 | 2000 | 0.5575 | 44.7575 |
| 0.2301 | 2.6572 | 3000 | 0.5473 | 44.0803 |
| 0.2145 | 3.5430 | 4000 | 0.5405 | 43.8474 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 7
Model tree for pnr-svc/whisper-tiny-turkish-speech-v1
Base model
openai/whisper-tiny