<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
whisper-medium-ft-B8
This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3234
- Wer: 13.6289
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.4871 | 0.4 | 50 | 0.5056 | 20.1970 |
| 0.4457 | 0.8 | 100 | 0.3678 | 16.7488 |
| 0.2877 | 1.2 | 150 | 0.3431 | 15.5993 |
| 0.1399 | 1.6 | 200 | 0.3326 | 17.4056 |
| 0.129 | 2.0 | 250 | 0.3234 | 13.6289 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cpu
- Datasets 2.12.0
- Tokenizers 0.13.3
