---
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-large-v3-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-large-v3-basque

This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1658
- Wer: 8.3543

## 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: 256
- eval_batch_size: 32
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 512
- total_eval_batch_size: 64
- 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     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.0865        | 0.66  | 500  | 0.1567          | 11.7156 |
| 0.0529        | 1.32  | 1000 | 0.1355          | 8.9309  |
| 0.0488        | 1.98  | 1500 | 0.1251          | 8.4340  |
| 0.0347        | 2.64  | 2000 | 0.1251          | 7.8145  |
| 0.0246        | 3.3   | 2500 | 0.1301          | 7.5569  |
| 0.0232        | 3.96  | 3000 | 0.1298          | 9.0719  |
| 0.0167        | 4.62  | 3500 | 0.1392          | 8.0905  |
| 0.0108        | 5.28  | 4000 | 0.1533          | 8.9493  |
| 0.0107        | 5.94  | 4500 | 0.1526          | 8.9738  |
| 0.0072        | 6.61  | 5000 | 0.1658          | 8.3543  |


### Framework versions

- Transformers 4.38.0
- Pytorch 2.1.1+cu121
- Datasets 2.8.0
- Tokenizers 0.15.2