Whisper Small Finetune - IERG4320 Project
This model is a fine-tuned version of openai/whisper-small on the Common Voice 13 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4611
- Wer Ortho: 21.8030
- Wer: 17.7395
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: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.3126 | 1.0 | 236 | 0.3930 | 20.1118 | 16.6297 |
| 0.2087 | 2.0 | 472 | 0.3943 | 20.3481 | 16.7697 |
| 0.1397 | 3.0 | 708 | 0.4087 | 20.5047 | 16.7103 |
| 0.088 | 4.0 | 944 | 0.4326 | 21.4326 | 17.3934 |
| 0.0491 | 5.0 | 1180 | 0.4611 | 21.8030 | 17.7395 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1
- Datasets 3.1.0
- Tokenizers 0.20.4
- Downloads last month
- 77
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for JerryLearnCode/4320-whisper-small-eng-0.03train-partial
Base model
openai/whisper-small