---
language:
- ms
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
datasets:
- clt013/malay-speech-1.6-million-rows-dataset
metrics:
- wer
model-index:
- name: Whisper Large v3 FT Malay - CLT013
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Malay Speech 1.6 million
      type: clt013/malay-speech-1.6-million-rows-dataset
      config: default
      split: train
      args: default
    metrics:
    - name: Wer
      type: wer
      value: 33.069727071077246
---

<!-- 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 v3 FT Malay - CLT013

This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the Malay Speech 1.6 million dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5227
- Wer: 33.0697

## 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: 2e-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: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.6896        | 0.2   | 1000 | 0.7044          | 40.9683 |
| 0.634         | 0.4   | 2000 | 0.6366          | 40.5439 |
| 0.5836        | 0.6   | 3000 | 0.5821          | 34.3331 |
| 0.5568        | 0.8   | 4000 | 0.5446          | 33.6870 |
| 0.535         | 1.0   | 5000 | 0.5227          | 33.0697 |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1