---
library_name: transformers
license: cc-by-nc-4.0
base_model: facebook/nllb-200-distilled-600M
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: nllb-200-distilled-600M-FLEURS-GL-EN
  results: []
datasets:
- juanjucm/FLEURS-SpeechT-GL-EN
language:
- gl
- en
---


# nllb-200-distilled-600M-FLEURS-GL-EN

This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) trained on [juanjucm/FLEURS-SpeechT-GL-EN](https://huggingface.co/datasets/juanjucm/FLEURS-SpeechT-GL-EN) for **Galician-to-Englis Machine Translation** task. It takes Galician texts as input and generates the correspondant English translation.

This Machine Translation model, was developed to be the second stage of a Speech Translation cascade system for transcribing and translating Galician audios into English texts. [This STT model](https://huggingface.co/juanjucm/whisper-large-v3-turbo-FLEURS-GL) can be used as a first step to transcribe Galician audio into text. After that, this MT model can be applied over the generated Galician transcriptions to get English text translations.

The motivation behind this work is to increase the visibility of the Galician language, making it more accessible for non-Galician speakers to understand and engage with Galician audio content.

This model was developed during a 3-week Speech Translation workshop organised by [Yasmin Moslem](https://huggingface.co/ymoslem).


### Performance and training details

Baseline model achieved a BLEY score of **39.98** on the evaluation dataset.

After fine-tuning, it achieves the following results on the evaluation set:
- Loss: 0.0877
- **BLEU: 43.7516**

The following hyperparameters were used during training:

- learning_rate: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8

### Training results

We used [BLEU Score](https://en.wikipedia.org/wiki/BLEU) as our reference translation metric for selecting the best checkpoint after training.

| Training Loss | Epoch | Step | Validation Loss | Bleu    |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| No log        | 1.0   | 343  | 5.3970          | 42.8151 |
| 14.0381       | 2.0   | 686  | 3.4256          | 42.6804 |
| 6.6148        | 3.0   | 1029 | 1.7277          | 42.9270 |
| 6.6148        | 4.0   | 1372 | 0.6586          | 43.0670 |
| 2.2397        | 5.0   | 1715 | 0.2392          | 43.7306 |
| 0.532         | 6.0   | 2058 | 0.1265          | 43.0986 |
| 0.532         | 7.0   | 2401 | 0.0939          | 43.4517 |
| 0.2069        | 8.0   | 2744 | 0.0877          | 43.7516 |


### Framework versions

- Transformers 4.47.1
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0