---
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: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# Whisper Turbo Multilingual (ko, ja, zh, en)

This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/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