metadata
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: vi
results: []
vi
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: 0.6612
- Wer: 1.2655
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 |
|---|---|---|---|---|
| 0.0204 | 5.59 | 1000 | 0.5415 | 1.3689 |
| 0.0005 | 11.17 | 2000 | 0.6213 | 1.2094 |
| 0.0003 | 16.76 | 3000 | 0.6507 | 1.2515 |
| 0.0002 | 22.35 | 4000 | 0.6612 | 1.2655 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 1.12.1
- Datasets 2.15.0
- Tokenizers 0.15.0