Hypa Orpheus 3b 0.1 Ft Unsloth Merged 16bit

🚀 Hypa_Orpheus-3b-0.1-ft (merged 16-bit)

A memory-efficient, 16-bit quantized and merged fine-tuned version of the Orpheus model, optimized for expressive multilingual text-to-speech, especially in low-resource African languages.

This model is a fine-tuned variant of canopylabs/orpheus-3b-0.1-ft, optimized with Unsloth and LoRA. It's designed for expressive multilingual TTS, with a focus on low-resource African languages. Key capabilities include:

• Text-to-Speech generation
• Speech synthesis for under-represented accents
• Voice cloning & emotion synthesis
• Research on multilingual low-resource voice AI

✨ Features

Model Details

Model Summary

This model was trained on a parallel text-speech dataset that includes over 300 hours (75k samples) of Nigerian-accented and low-resource language audio (Igbo, Yoruba, Hausa). A significant portion of the dataset comes from AfroVoices' transcription of real-world YouTube data (Random speaker, ~100+ hrs). To maintain and enhance multilingual capabilities while preventing catastrophic forgetting, synthetic speech-text data sampled from the original 8 Orpheus voices using default emotional prompts was included. The final training set also incorporated new speakers:

• Eniola (40 hrs) – Female, bold, clear
• Moyo (40 hrs) – Female, professional, articulate
• Lovelyn (35 hrs) – Female, warm, shy
• Precious (30 hrs) – Female, friendly, gentle

This model achieves state-of-the-art performance on low-resource Multilingual TTS tasks across African languages (see training stats below).

Base Model Details

The default Orpheus-TTS model released by Canopy Labs supports the following voices and emotions:

Voices: tara, leah, jess, leo, dan, mia, zac, and zoe.

Emotions: <laugh>, <chuckle>, <sigh>, <cough>, <sniffle>, <groan>, <yawn>, and <gasp>.

Through synthetic data generation and addition, our finetuned model also retains these voices and emotions. For more information on voices and emotions, please visit the default model's card.

Our Model Sample Generations

🎧 Listen to samples generated by Hypa Orpheus-TTS

📦 Training Details

Training Summary

• Base model: canopylabs/orpheus-3b-0.1-ft
• Training engine: Unsloth + LoRA
• LoRA config: r=1024, alpha=1024, dropout=0.0, full attention + FFN adaptation
• Quantization: 4-bit (bnb) for training; final model is highly memory-efficient
• Total steps: 18,014 (1 epoch)
• Batch size: 1 × 4 (grad accum)
• GPU: A100 40GB (max 55% VRAM used)

Dataset Summary

• Sources:
  • ✅ Manually aligned YouTube transcriptions (aka Random)
  • ✅ Synthetic voice generation from Orpheus TTS
  • ✅ Parallel text-audio pairs for African-English, Igbo, Yoruba, Hausa
• Total Hours: 300+ (multi-accent)
• Key Speakers: 45+ unique voices (see speaker distribution chart below)

We plan to open-source the full dataset shortly similar to the Hypa_Fleurs initiative.

📄 Licensing and Citation

This model is released under an Open Source License (apache-2.0). Please refer to the LICENSE file for full details.

When using this model in your work, please cite both this model as well as the base canopylabs/orpheus-3b-0.1-ft model as follows:

@misc{canopylabsorpheus,
  title={Orpheus-3b-0.1-ft: A Multilingual Text-to-Speech Model},
  author={Canopy Labs},
  year={2025},
  publisher={Hugging Face},
  howpublished={\url{https://huggingface.co/canopylabs/orpheus-3b-0.1-ft}},
  note={Fine-tuned version of Orpheus for expressive TTS}
}

@misc{hypaorpheus4bit,
  title={Hypa_Orpheus-3b-0.1-ft (LoRA-4bit)},
  author={Hypa AI},
  year={2025},
  note={Fine-tuned Orpheus TTS on African languages},
  url={https://huggingface.co/hypaai/Hypa_Orpheus-3b-0.1-ft-unsloth-bnb-4bit}
}

👏 Acknowledgements

• Canopy Labs Team: For creating the foundational model and opensourcing it.
• AfroVoices Experts: For their translation expertise and high-quality datasets.
• Community Support: We thank all supporters, contributors, and users.

📞 Contact and Contributions

For any questions, issues, or contributions, please open an issue in this repository or contact hypa.ai.ng@gmail.com. Contributions are welcome!

🌟 Closing Remarks

By making Hypa_Orpheus available, we hope to empower research and development in multilingual speech technologies for African languages.

Hypa AI remains steadfast in its mission to pioneer intelligent solutions that are not just technologically advanced but are also culturally aware, ensuring that the future of AI is as diverse and inclusive as the world it serves.

AfroVoices, a subsidiary of Hypa AI, is dedicated to amplifying African voices, languages, and cultures in the intelligence age. Focused on bridging the digital representation gap, AfroVoices curates datasets and resources for African languages, promoting inclusivity and cultural appreciation in AI technologies. Their mission goes beyond technological innovation, aiming to celebrate the richness of African linguistic diversity on a global stage.

💻 Usage

Unsloth Inference

Download the needed packages.

%%capture
import os
if "COLAB_" not in "".join(os.environ.keys()):
    !pip install unsloth
else:
    # Do this only in Colab notebooks! Otherwise use pip install unsloth
    !pip install --no-deps bitsandbytes accelerate xformers==0.0.29.post3 peft trl==0.15.2 triton cut_cross_entropy unsloth_zoo
    !pip install sentencepiece protobuf datasets huggingface_hub hf_transfer
    !pip install --no-deps unsloth
!pip install snac

Download the models (both the SNAC encoder/decoder as well as our finetuned Hypa_Orpheus).

import torch
from snac import SNAC
from unsloth