Whisper openai-whisper-tiny
This model is a fine-tuned version of openai/whisper-tiny on the llamadas ecu911 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3641
- Wer: 67.4731
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: 2
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 3
- total_train_batch_size: 6
- total_eval_batch_size: 3
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.0235 | 7.9365 | 500 | 1.1164 | 94.9283 |
| 0.4493 | 15.8730 | 1000 | 0.6714 | 78.4767 |
| 0.2341 | 23.8095 | 1500 | 0.4407 | 66.3620 |
| 0.1679 | 31.7460 | 2000 | 0.3641 | 67.4731 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1