---
base_model: openai/whisper-small
datasets:
- fruk19/S_asr
language:
- th
license: apache-2.0
metrics:
- wer
tags:
- generated_from_trainer
model-index:
- name: South_asri
  results:
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      name: aicookcook
      type: fruk19/S_asr
      config: default
      split: None
      args: 'config: th'
    metrics:
    - type: wer
      value: 17.85503355704698
      name: Wer
---

<!-- 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. -->

# South_asri

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the aicookcook dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1529
- Wer: 17.8550

## 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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 99
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.2359        | 1.0   | 3000 | 0.1905          | 22.4242 |
| 0.1383        | 2.0   | 6000 | 0.1575          | 18.8403 |
| 0.0786        | 3.0   | 9000 | 0.1529          | 17.8550 |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.0.1+cu117
- Datasets 2.20.0
- Tokenizers 0.19.1