---
license: apache-2.0
base_model: duytran3112/whisper-sm-vivos
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-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-vietnamese

This model is a fine-tuned version of [duytran3112/whisper-sm-vivos](https://huggingface.co/duytran3112/whisper-sm-vivos) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5021
- Wer: 143.3132
- Cer: 170.7314

## 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

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer      | Cer      |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
| 0.1927        | 3.07  | 1000 | 0.4454          | 99.8576  | 86.3335  |
| 0.0144        | 6.13  | 2000 | 0.4553          | 190.2670 | 169.4322 |
| 0.0029        | 9.2   | 3000 | 0.4889          | 144.1729 | 165.2591 |
| 0.0018        | 12.27 | 4000 | 0.5021          | 143.3132 | 170.7314 |


### Framework versions

- Transformers 4.31.0
- Pytorch 2.0.0
- Datasets 2.14.4
- Tokenizers 0.13.3