---
library_name: peft
language:
- zh
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
- wft
- whisper
- automatic-speech-recognition
- audio
- speech
- generated_from_trainer
datasets:
- JacobLinCool/common_voice_19_0_zh-TW
model-index:
- name: whisper-large-v3-turbo-common_voice_19_0-zh-TW-full-2
  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-large-v3-turbo-common_voice_19_0-zh-TW-full-2

This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on the JacobLinCool/common_voice_19_0_zh-TW dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.1786
- eval_wer: 32.5554
- eval_cer: 8.6009
- eval_decode_runtime: 90.9833
- eval_wer_runtime: 0.1257
- eval_cer_runtime: 0.1534
- eval_runtime: 297.9052
- eval_samples_per_second: 16.828
- eval_steps_per_second: 0.527
- epoch: 3.0737
- step: 5000

## 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: 0.0002
- train_batch_size: 4
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 5000

### Framework versions

- PEFT 0.13.2
- Transformers 4.46.1
- Pytorch 2.4.0
- Datasets 3.0.2
- Tokenizers 0.20.1