---
library_name: transformers
pipeline_tag: automatic-speech-recognition
language:
- khm
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper Finetuned for Khmer
  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 Finetuned for Khmer

This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0204
- Wer: 0.0998

## 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: 32
- eval_batch_size: 32
- 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
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 0.0252        | 0.7722 | 200  | 0.0256          | 0.1182 |
| 0.0193        | 1.5444 | 400  | 0.0219          | 0.1037 |
| 0.0099        | 2.3166 | 600  | 0.0204          | 0.0998 |


### Framework versions

- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1