---
base_model: openai/whisper-small
datasets:
- arrow
language:
- yue
library_name: peft
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: Whisper Small Cantonese
  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 Small Cantonese

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Multi-Domain Cantonese Corpus (MDCC) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1055
- Cer: 15.5362

## 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: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Cer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.038         | 0.9606 | 1000 | 0.1068          | 20.1761 |
| 0.0436        | 1.9212 | 2000 | 0.1055          | 15.5362 |


### Framework versions

- PEFT 0.13.0
- Transformers 4.45.1
- Pytorch 2.4.0+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0