---
library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
- whisper-event
- generated_from_trainer
datasets:
- asierhv/composite_corpus_eu_v2.1
language:
- eu
metrics:
- wer
model-index:
- name: Whisper Small Basque
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Common Voice 17.0
      type: mozilla-foundation/common_voice_17_0
      config: eu
      split: test
      args:
        language: eu
    metrics:
      - name: Test WER
        type: wer
        value: 8.33
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: asierhv/composite_corpus_eu_v2.1
      type: asierhv/composite_corpus_eu_v2.1
    metrics:
    - name: Wer
      type: wer
      value: 10.886229784051602
---

<!-- 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 the asierhv/composite_corpus_eu_v2.1 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1836
- Wer: 10.8862
- Wer on Mozilla Common Voice, `test` split: **8.33**

## 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: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 8000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.3998        | 0.125 | 1000 | 0.3651          | 21.5014 |
| 0.1975        | 0.25  | 2000 | 0.2918          | 15.8736 |
| 0.1433        | 0.375 | 3000 | 0.2721          | 13.9011 |
| 0.1925        | 0.5   | 4000 | 0.2565          | 12.7372 |
| 0.0818        | 0.625 | 5000 | 0.2563          | 11.9426 |
| 0.1038        | 0.75  | 6000 | 0.2390          | 11.0732 |
| 0.1282        | 0.875 | 7000 | 0.2344          | 11.3910 |
| 0.0959        | 1.0   | 8000 | 0.1836          | 10.8862 |


### Framework versions

- Transformers 4.49.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.2.1.dev0
- Tokenizers 0.21.0