---
language:
- vi
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper Small Vietnamese - Nhi Le
  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 Small Vietnamese - Nhi Le

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Vietnamese ASR Custom Corpus dataset.
It achieves the following results on the evaluation set:
- Loss: 2.3541
- Wer: 56.0841

## 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: 2
- training_steps: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 4.6449        | 0.02  | 2    | 4.3170          | 30.7461 |
| 3.4276        | 0.04  | 4    | 2.9799          | 32.8493 |
| 2.7302        | 0.07  | 6    | 2.6128          | 30.0451 |
| 2.0397        | 0.09  | 8    | 2.4305          | 33.7506 |
| 2.0823        | 0.11  | 10   | 2.3541          | 56.0841 |


### Framework versions

- Transformers 4.36.0
- Pytorch 2.1.1+cpu
- Datasets 2.15.0
- Tokenizers 0.15.0