metadata
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-medium-ft-noise
results: []
whisper-medium-ft-noise
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: 0.1914
- Wer: 8.3898
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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2895 | 1.0 | 1385 | 0.1664 | 9.7065 |
| 0.0874 | 2.0 | 2770 | 0.1526 | 9.4056 |
| 0.0374 | 3.0 | 4155 | 0.1629 | 9.1986 |
| 0.0139 | 4.0 | 5540 | 0.1702 | 8.5403 |
| 0.004 | 5.0 | 6925 | 0.1843 | 8.5779 |
| 0.001 | 6.0 | 8310 | 0.1914 | 8.3898 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3