metadata
library_name: peft
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
- base_model:adapter:openai/whisper-large-v3-turbo
- lora
- transformers
metrics:
- wer
model-index:
- name: model
results: []
model
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0984
- Wer: 12.1817
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: 16
- eval_batch_size: 8
- seed: 42
- 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: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0432 | 4.2373 | 1000 | 0.0928 | 13.0043 |
| 0.0211 | 8.4746 | 2000 | 0.0946 | 13.2132 |
| 0.0126 | 12.7119 | 3000 | 0.0959 | 12.5996 |
| 0.0136 | 16.9492 | 4000 | 0.0984 | 12.1817 |
Framework versions
- PEFT 0.17.1
- Transformers 4.55.2
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.4