metadata
library_name: transformers
language:
- en
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper Tiny
results: []
Whisper Tiny
This model is a fine-tuned version of openai/whisper-tiny on the Personal - Mimic Recording dataset. It achieves the following results on the evaluation set:
- Loss: 0.3751
- Wer: 0.1311
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5941 | 1.0 | 293 | 0.4660 | 0.2291 |
| 0.2868 | 2.0 | 586 | 0.4858 | 0.2960 |
| 0.1692 | 3.0 | 879 | 0.4274 | 0.2219 |
| 0.0971 | 4.0 | 1172 | 0.4568 | 0.2014 |
| 0.0562 | 5.0 | 1465 | 0.4665 | 0.1820 |
| 0.0291 | 6.0 | 1758 | 0.4346 | 0.1801 |
| 0.0124 | 7.0 | 2051 | 0.3950 | 0.1456 |
| 0.0024 | 8.0 | 2344 | 0.3777 | 0.1359 |
| 0.0006 | 9.0 | 2637 | 0.3756 | 0.1323 |
| 0.0002 | 10.0 | 2930 | 0.3751 | 0.1311 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0