---
base_model: openai/whisper-small
datasets:
- mozilla-foundation/common_voice_16_1
language:
- nan
library_name: peft
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: Whisper small Taiwanese - LoRA
  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 Taiwanese - LoRA

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.1 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9261

## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.0204        | 1.0   | 2572  | 1.0091          |
| 0.9044        | 2.0   | 5144  | 0.9392          |
| 0.7166        | 3.0   | 7716  | 0.8862          |
| 0.5224        | 4.0   | 10288 | 0.9016          |
| 0.5268        | 5.0   | 12860 | 0.8868          |
| 0.414         | 6.0   | 15432 | 0.9129          |
| 0.3592        | 7.0   | 18004 | 0.9097          |
| 0.2912        | 8.0   | 20576 | 0.9261          |


### Framework versions

- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2