---
library_name: peft
language:
- th
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
metrics:
- wer
model-index:
- name: Whisper Large v3 Thai Finetuned
  results:
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      name: Common Voice 17.0
      type: mozilla-foundation/common_voice_17_0
      config: th
      split: None
      args: 'config: th, split: train'
    metrics:
    - type: wer
      value: 77.07049551458215
      name: Wer
---

<!-- 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 Large v3 Thai Finetuned

This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the Common Voice 17.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1953
- Cer: 49.5719
- Wer: 77.0705

## 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: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use paged_adamw_8bit 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
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Cer      | Wer      |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.158         | 1.0   | 2052  | 0.1361          | 288.0891 | 56.6543  |
| 0.1166        | 2.0   | 4104  | 0.1296          | 232.8857 | 57.0405  |
| 0.0739        | 3.0   | 6156  | 0.1298          | 107.5882 | 42.6799  |
| 0.0467        | 4.0   | 8208  | 0.1370          | 61.4281  | 43.2440  |
| 0.0263        | 5.0   | 10260 | 0.1424          | 69.8588  | 80.9373  |
| 0.012         | 6.0   | 12312 | 0.1607          | 56.1242  | 68.8006  |
| 0.0081        | 7.0   | 14364 | 0.1649          | 130.1459 | 76.1770  |
| 0.0036        | 8.0   | 16416 | 0.1782          | 110.6614 | 116.6100 |
| 0.002         | 9.0   | 18468 | 0.1862          | 50.2801  | 85.8464  |
| 0.0005        | 10.0  | 20520 | 0.1953          | 49.5719  | 77.0705  |


### Framework versions

- PEFT 0.14.1.dev0
- Transformers 4.49.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0