---
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-small-basque
  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-small-basque

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1906
- Wer: 9.5417

## 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: 128
- eval_batch_size: 32
- 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     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.17          | 0.33  | 1000 | 0.2697          | 15.6613 |
| 0.1163        | 0.66  | 2000 | 0.2198          | 11.7272 |
| 0.0966        | 0.99  | 3000 | 0.2009          | 10.2785 |
| 0.073         | 1.32  | 4000 | 0.1945          | 9.8476  |
| 0.0666        | 1.65  | 5000 | 0.1906          | 9.5417  |


### Framework versions

- Transformers 4.25.1
- Pytorch 2.5.1+cu121
- Datasets 2.8.0
- Tokenizers 0.13.3