metadata
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-med-LoRA_r256_a128
results: []
whisper-med-LoRA_r256_a128
This model is a fine-tuned version of openai/whisper-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2540
- Wer: 11.7332
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.668 | 1.0 | 2801 | 0.3934 | 16.5106 |
| 0.3058 | 2.0 | 5602 | 0.3089 | 13.8926 |
| 0.2528 | 3.0 | 8403 | 0.2773 | 12.0390 |
| 0.2256 | 4.0 | 11204 | 0.2583 | 11.6568 |
| 0.2106 | 5.0 | 14005 | 0.2540 | 11.7332 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3