Mano-MT-Khmer Β· Mano αž˜αž“αŸ„ Khmer ↔ English translation

Work in progress: no model weights here yet. This repo will hold the first model when it is trained and tested.

Mano ("mind") will translate between Khmer and English, small enough to run offline on a phone or an ordinary CPU. It belongs to the same family as Sota (ASR, listens), Chakkhu (OCR, reads), Tossana (captioning, sees), Akkhara (keyboard, types) and VoxPocket (TTS, speaks).

Mano architecture

Planned design (β‰ˆ29M parameters, estimate)

  • Trained from scratch on Khmer–English sentence pairs (open licenses only)
  • Tokens: the same 3,402 Khmer cluster tokens as Chakkhu and Sota, plus English subwords
  • Both directions in one model
  • Export: int8 ONNX

Status

Step Result
Parallel text (Khmer–English) collecting
First model soon

License

To be decided with the first release.

Citation

@misc{ing2026mano,
  author    = {Ing, Muyleang},
  title     = {Mano: Khmer ↔ English translation},
  year      = {2026},
  publisher = {Hugging Face},
  url       = {https://huggingface.co/muyleanging/Mano-MT-Khmer}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Collection including muyleanging/Mano-MT-Khmer