Open Source Models

Model Catalog

Translation models for low-resource African languages. Community-built, open-sourced, and ready to deploy.

4

Total

1

Live

0

Training

3

Planned

Try Live Translation1 model online

Quick Start

Python · Hugging Face Transformers

inference.py
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained('sheikhtijan/nllb-mandinka-english')
tokenizer = AutoTokenizer.from_pretrained('sheikhtijan/nllb-mandinka-english')

# Mandinka → English
tokenizer.src_lang = "bam_Latn"
inputs = tokenizer("Ali be fereeadaa la.", return_tensors="pt")
output = model.generate(**inputs,
    forced_bos_token_id=tokenizer.convert_tokens_to_ids("eng_Latn"))
print(tokenizer.decode(output[0], skip_special_tokens=True))

Help build the next model

Every translation you contribute brings us closer to training the next model.

Start Contributing Try Live