---
library_name: transformers
language:
- zh
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
metrics:
- wer
model-index:
- name: Whisper Taiwanese Small3 - Steven Wang
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Common Voice 17.0
      type: mozilla-foundation/common_voice_17_0
      config: nan-tw
      split: None
      args: 'config: zh, split: test'
    metrics:
    - name: Wer
      type: wer
      value: 90.87361803598526
---

<!-- 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 Taiwanese Small3 - Steven Wang

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 17.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7512
- Wer: 90.8736

## 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 | Wer     |
|:-------------:|:-------:|:----:|:---------------:|:-------:|
| 0.083         | 2.9240  | 1000 | 0.6382          | 93.2582 |
| 0.0111        | 5.8480  | 2000 | 0.6895          | 91.6323 |
| 0.0019        | 8.7719  | 3000 | 0.7383          | 91.1771 |
| 0.0009        | 11.6959 | 4000 | 0.7512          | 90.8736 |


### Framework versions

- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0