metadata
library_name: peft
language:
- multilingual
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper Turbo Multilingual (ko, ja, zh, en)
results: []
Whisper Turbo Multilingual (ko, ja, zh, en)
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the custom_multilingual dataset. It achieves the following results on the evaluation set:
- Loss: 0.3434
- Wer: 25.3086
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: 0.001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use 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: 5
- training_steps: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6956 | 0.1754 | 10 | 0.4175 | 32.7160 |
| 0.2372 | 0.3509 | 20 | 0.3434 | 25.3086 |
Framework versions
- PEFT 0.15.2.dev0
- Transformers 4.46.3
- Pytorch 2.3.1+cu121
- Datasets 3.0.0
- Tokenizers 0.20.3