Whisper ASR Asanti Twi
This model is a fine-tuned version of openai/whisper-turbo on the kojo-george/asanti-twi-tts dataset. It achieves the following results on the evaluation set:
- Loss: 0.2205
- Wer: 18.3988
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
- 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
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.226 | 0.5666 | 1000 | 0.3430 | 25.6197 |
| 0.1438 | 1.1331 | 2000 | 0.2737 | 20.8776 |
| 0.1277 | 1.6997 | 3000 | 0.2353 | 18.9530 |
| 0.083 | 2.2663 | 4000 | 0.2205 | 18.3988 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 7
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.