---
license: apache-2.0
base_model: biodatlab/whisper-th-small-combined
tags:
- generated_from_trainer
datasets:
- common_voice_17_0
metrics:
- wer
model-index:
- name: Whisper-small-thai
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: common_voice_17_0
      type: common_voice_17_0
      config: th
      split: test
      args: th
    metrics:
    - name: Wer
      type: wer
      value: 55.432891743610334
---

<!-- 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-thai

This model is a fine-tuned version of [biodatlab/whisper-th-small-combined](https://huggingface.co/biodatlab/whisper-th-small-combined) on the common_voice_17_0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1073
- Wer: 55.4329

## 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: 5000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.3415        | 0.3647 | 1000 | 0.1371          | 65.4958 |
| 0.1638        | 0.7294 | 2000 | 0.1253          | 60.3238 |
| 0.1995        | 1.0941 | 3000 | 0.1161          | 57.4736 |
| 0.213         | 1.4588 | 4000 | 0.1104          | 56.2358 |
| 0.2041        | 1.8235 | 5000 | 0.1073          | 55.4329 |


### Framework versions

- Transformers 4.43.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1