Whisper Medium en
This model is a fine-tuned version of openai/whisper-medium on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3150
- Wer: 10.7396
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: 32
- 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 |
---|---|---|---|---|
0.2714 | 0.2 | 1000 | 0.3230 | 11.4694 |
0.1778 | 1.195 | 2000 | 0.3191 | 11.2809 |
0.1435 | 2.19 | 3000 | 0.3188 | 11.1639 |
0.0461 | 3.185 | 4000 | 0.3441 | 11.1333 |
0.1327 | 4.18 | 5000 | 0.3150 | 10.7396 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 45
Unable to determine this model's library. Check the
docs
.
Model tree for deepdml/whisper-medium-en-cv17
Base model
openai/whisper-mediumDataset used to train deepdml/whisper-medium-en-cv17
Evaluation results
- Wer on Common Voice 17.0test set self-reported10.740
- WER on google/fleurstest set self-reported7.470
- WER on facebook/voxpopulitest set self-reported9.060