Whisper Tiny en
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6106
- Wer: 25.8615
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: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4769 | 1.0974 | 1000 | 0.6212 | 26.6080 |
| 0.346 | 3.0922 | 2000 | 0.6184 | 26.1229 |
| 0.3654 | 5.087 | 3000 | 0.6130 | 26.0782 |
| 0.2858 | 7.0818 | 4000 | 0.6196 | 26.2060 |
| 0.3308 | 9.0766 | 5000 | 0.6106 | 25.8615 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 12
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.
Model tree for deepdml/whisper-tiny-en-cv17
Base model
openai/whisper-tinyDataset used to train deepdml/whisper-tiny-en-cv17
Evaluation results
- Wer on Common Voice 17.0test set self-reported25.862
- WER on google/fleurstest set self-reported15.970
- WER on facebook/voxpopulitest set self-reported18.480