---
license: mit
library_name: transformers
---

# Swahili-English Translation Model

## Model Details

- **Pre-trained Model**: Helsinki-NLP/opus-mt-en-sw
- **Architecture**: Transformer
- **Training Data**: Fine-tuned on 1,710,223 English-Swahili sentence pairs
- **Base Model**: Helsinki-NLP/opus-mt-en-sw
- **Training Method**: Fine-tuned with an emphasis on bidirectional translation between Swahili and English.

### Model Description

This Swahili-English translation model was developed to handle translations between Swahili, one of Africa's most spoken languages, and English. It was fine-tuned on a large dataset of English-Swahili sentence pairs, leveraging the Transformer architecture for effective translation.

- **Developed by:** Otieno Bildad Moses
- **Model Type:** Transformer
- **Languages:** Swahili, English
- **License:** Distributed under the MIT License

### Training Data

The model was fine-tuned on the following dataset:

- **OPUS-HPLT:**
  - **Package**: [en-sw.txt.zip](https://object.pouta.csc.fi/OPUS-HPLT/v1.1/moses/en-sw.txt.zip)
  - **License**: [CC-BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/legalcode)
  - **Citation**: Holger Schwenk et al., WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia, arXiv, July 2019.

## Usage

### Using a Pipeline as a High-Level Helper

```python
from transformers import pipeline

# Initialize the translation pipeline
translator = pipeline("translation", model="Bildad/English-Swahili_Translation")

# Translate text
translation = translator("Habari yako?")[0]
translated_text = translation["translation_text"]

print(translated_text)