MarianMT English to Kabyle Translation Model

This is a fine-tuned MarianMT model for translating from English (en) to Kabyle (kab), a northen african and a Tamaziɣt (Berber) language spoken primarily in Algeria (and some parts of the world).

Model Description

• Model Type: MarianMT (Transformer-based Neural Machine Translation)
• Architecture: Encoder-Decoder with 6 layers each
• Languages: English (en) → Kabyle (kab)
• Checkpoint: 24000 training steps
• Framework: PyTorch / Transformers

Intended Use

• Machine translation from English to Kabyle
• Research in low-resource language translation
• Applications supporting Kabyle language preservation and accessibility

How to Use

Quick Start with Pipeline

from transformers import pipeline

# Load the translation pipeline
translator = pipeline("translation", model="boffire/marianmt-en-kab", device=0)

# Translate text
result = translator("Hello, how are you?", max_length=128)
print(result[0]['translation_text'])