---
language:
- vi
license: apache-2.0
base_model: openai/whisper-base
tags:
- hf-asr-leaderboard
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper Base Mnong
  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 Base Mnong

This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the MnongAudio-v2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7309
- Wer: 78.4474

## 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
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer      |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 1.2709        | 2.0325 | 1000 | 1.3573          | 121.7936 |
| 0.5929        | 4.0650 | 2000 | 0.9105          | 81.5333  |
| 0.2907        | 6.0976 | 3000 | 0.7671          | 80.9065  |
| 0.204         | 8.1301 | 4000 | 0.7309          | 78.4474  |


### Framework versions

- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1