---
license: apache-2.0
base_model: JRHuy/whisper-vietnamese-2
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-medium-vietnamese
  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-medium-vietnamese

This model is a fine-tuned version of [JRHuy/whisper-vietnamese-2](https://huggingface.co/JRHuy/whisper-vietnamese-2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4836
- Wer: 15.8204
- Cer: 8.7789

## 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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 500
- training_steps: 4000

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     | Cer    |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|
| 0.0069        | 2.87  | 1000 | 0.4490          | 16.3409 | 9.1222 |
| 0.0042        | 5.73  | 2000 | 0.4687          | 15.7427 | 8.5273 |
| 0.0033        | 8.6   | 3000 | 0.4829          | 15.6754 | 8.5060 |
| 0.0022        | 11.46 | 4000 | 0.4836          | 15.8204 | 8.7789 |


### Framework versions

- Transformers 4.32.0
- Pytorch 2.0.0
- Datasets 2.14.4
- Tokenizers 0.13.3