Whisper tiny epoch 1- Perrie
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4304
- Cer: 60.2188
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: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 70
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.3925 | 1.0 | 705 | 0.4304 | 60.2188 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 1.12.1
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 7
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Perrie/whisper-tiny-epoch-1
Base model
openai/whisper-tiny