---
library_name: transformers
language:
- es
- en
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
datasets:
- facebook/covost2
metrics:
- bleu
model-index:
- name: Whisper-large-v3-for-translation
  results:
  - task:
      name: Translation
      type: translation
    dataset:
      name: covost2
      type: facebook/covost2
      config: es_en
      split: None
      args: 'config: es, split: test, train'
    metrics:
    - name: Bleu
      type: bleu
      value: 41.85386637078158
---

<!-- 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-for-translation

This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the covost2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7779
- Bleu: 41.8539

## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 1
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Bleu    |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.6494        | 1.0   | 4939 | 0.7779          | 41.8539 |


### Framework versions

- Transformers 4.45.2
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3