README.md

metadata

title: English-Ibono Translation API
emoji: 🌍
colorFrom: blue
colorTo: green
sdk: docker
app_file: app.py
app_port: 7860

English-to-Ibono Translation API

This Hugging Face Space hosts a Flask API that provides translations from English to Ibono using a fine-tuned t5-small model.

The model was fine-tuned on a small dataset collected via the IBN-AI application.

API Endpoint

• URL: /translate
• Method: POST
• Request Body (JSON):

  {
    "text": "Your English text here"
  }
  

• Response Body (JSON - Success):

  {
    "translation": "Translated Ibono text"
  }
  

• Response Body (JSON - Error):

  {
    "error": "Error message"
  }
  

How to Use

Send a POST request to the /translate endpoint of this Space's URL with the English text you want to translate in the JSON body.

Example using curl:

curl -X POST \
  https://YOUR_SPACE_NAME.hf.space/translate \
  -H 'Content-Type: application/json' \
  -d '{"text": "Hello world"}'

(Replace YOUR_SPACE_NAME.hf.space with the actual URL of this Space).

Model Details

• Base Model: t5-small
• Fine-tuning Data: ~189 English-Ibono pairs.
• Note: Due to the small dataset size, the translation quality is experimental and may be limited.

Files

• app.py: The Flask application script.
• requirements.txt: Python dependencies.
• model/: Directory containing the fine-tuned model files.
• README.md: This file (configuration for the Space).