<!-- 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-tiny-finetuned-minds14-en-us
This model is a fine-tuned version of openai/whisper-tiny on the MINDS-14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7170
- Wer Ortho: 0.3580
- Wer: 0.3579
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: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.3159 | 3.57 | 100 | 0.5309 | 0.3580 | 0.3553 |
| 0.0402 | 7.14 | 200 | 0.5889 | 0.3338 | 0.3301 |
| 0.0038 | 10.71 | 300 | 0.6554 | 0.3526 | 0.3495 |
| 0.0012 | 14.29 | 400 | 0.6934 | 0.3499 | 0.3495 |
| 0.0007 | 17.86 | 500 | 0.7170 | 0.3580 | 0.3579 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
