Whisper Small RU (Phone) v0.3 - Stepler
This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2292
- Wer: 18.7245
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
- total_train_batch_size: 16.0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5495 | 1.7483 | 1000 | 0.2292 | 18.7245 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu124
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- -
Model tree for Stepler/whisper-small-ru-phone-v0.3
Base model
openai/whisper-smallDataset used to train Stepler/whisper-small-ru-phone-v0.3
Evaluation results
- Wer on Common Voice 17.0test set self-reported18.725