metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: model_checkpoint
results: []
model_checkpoint
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3509
- Wer: 69.8851
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: 12
- 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 |
|---|---|---|---|---|
| 0.0805 | 1.88 | 1000 | 0.2634 | 74.4828 |
| 0.0242 | 3.77 | 2000 | 0.2649 | 73.1034 |
| 0.0068 | 5.65 | 3000 | 0.3314 | 72.4138 |
| 0.0005 | 7.53 | 4000 | 0.3509 | 69.8851 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2