---
language:
- zh
license: apache-2.0
base_model: openai/whisper-base
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_13_0
model-index:
- name: Whisper Base zh-TW
  results: []
pipeline_tag: automatic-speech-recognition
---

<!-- 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 Base zh-TW

This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Common Voice 13.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3403
- Cer: 16.6369

## 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: 16
- 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: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Cer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.0772        | 1.38  | 1000 | 0.3230          | 17.4367 |
| 0.0436        | 2.75  | 2000 | 0.3191          | 16.4661 |
| 0.0111        | 4.13  | 3000 | 0.3343          | 16.5334 |
| 0.0078        | 5.5   | 4000 | 0.3403          | 16.6369 |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2