whisper-tiny-asr-english
This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:
- Wer Ortho: 0.3196
- Wer: 0.3158
- Loss: 0.5223
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: 4
- eval_batch_size: 4
- 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 | Wer Ortho | Wer | Validation Loss |
---|---|---|---|---|---|
0.4862 | 0.89 | 100 | 0.3917 | 0.3719 | 0.5372 |
0.3213 | 1.79 | 200 | 0.3769 | 0.3571 | 0.4777 |
0.1822 | 2.68 | 300 | 0.3726 | 0.3589 | 0.4746 |
0.068 | 3.57 | 400 | 0.3276 | 0.3146 | 0.4819 |
0.0333 | 4.46 | 500 | 0.3196 | 0.3158 | 0.5223 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 22
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.