Whisper tiny by ehzawad
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2422
- Wer: 75.4095
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: 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 |
|---|---|---|---|---|
| 0.3593 | 0.53 | 1000 | 0.3717 | 102.7311 |
| 0.2502 | 1.07 | 2000 | 0.2802 | 81.0367 |
| 0.2219 | 1.6 | 3000 | 0.2535 | 80.8361 |
| 0.2069 | 2.14 | 4000 | 0.2422 | 75.4095 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 10
Dataset used to train ehzawad/whisper-tiny-bn
Evaluation results
- Wer on Common Voice 13.0test set self-reported75.409