---
library_name: transformers
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
model-index:
- name: test-whisper-tiny-th
  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. -->

# test-whisper-tiny-th

This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8860
- Cer: 35.4839

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | Cer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| No log        | 1.0   | 7    | 0.9718          | 37.0968 |
| 1.1407        | 2.0   | 14   | 0.9296          | 55.2419 |
| 0.895         | 3.0   | 21   | 0.9023          | 53.9315 |
| 0.895         | 4.0   | 28   | 0.8905          | 33.4677 |
| 0.8158        | 5.0   | 35   | 0.8860          | 35.4839 |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1