---
language:
- zh
license: apache-2.0
base_model: openai/whisper-medium
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_16_0
model-index:
- name: Whisper Small zh-TW - Chinese
  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 zh-TW - Chinese

This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 11.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1496
- Cer: 99.9924

## 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: 8
- eval_batch_size: 4
- 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      |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.1829        | 0.66  | 1000 | 0.1742          | 100.0076 |
| 0.0495        | 1.33  | 2000 | 0.1629          | 99.9824  |
| 0.044         | 1.99  | 3000 | 0.1497          | 99.9849  |
| 0.0193        | 2.65  | 4000 | 0.1496          | 99.9924  |


### Framework versions

- Transformers 4.36.2
- Pytorch 2.1.0.post301
- Datasets 2.16.1
- Tokenizers 0.15.0