---
license: apache-2.0
base_model: openai/whisper-large
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper_large_finetune_Formosa
  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_finetune_Formosa

This model is a fine-tuned version of [openai/whisper-large](https://huggingface.co/openai/whisper-large) on the Formosa dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1572
- Wer: 9.8143

## 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: 2000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.2883        | 0.1018 | 500  | 0.1850          | 13.1693 |
| 0.2687        | 0.2035 | 1000 | 0.1702          | 10.7376 |
| 0.2417        | 0.3053 | 1500 | 0.1626          | 10.1341 |
| 0.2628        | 0.4070 | 2000 | 0.1572          | 9.8143  |


### Framework versions

- Transformers 4.41.2
- Pytorch 1.13.1+cu116
- Datasets 2.20.0
- Tokenizers 0.19.1