metadata
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-medium-train_noise4
results: []
whisper-medium-train_noise4
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: 0.0105
- Wer: 2.0416
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 |
|---|---|---|---|---|
| 0.1666 | 1.0 | 2863 | 0.0897 | 6.6866 |
| 0.0337 | 2.0 | 5726 | 0.0348 | 3.5587 |
| 0.0088 | 3.0 | 8589 | 0.0206 | 2.5098 |
| 0.0025 | 4.0 | 11452 | 0.0124 | 2.3038 |
| 0.0008 | 5.0 | 14315 | 0.0110 | 1.9667 |
| 0.0002 | 6.0 | 17178 | 0.0105 | 2.0416 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3