Modelpublic

joyoh/mOrpheus_3B-1Base_early_preview-v1-25000_GGUF

sourceHugging Faceupdated 2mo agoView on Hugging Face

0likes81downloads

Model Card

mOrpheus3B-1Baseearly_preview (NSFW TTS)

A finetuned Orpheus text‑to‑speech model trained on adult data for more expressive sounds: <laugh>, <chuckle>, <sigh>, <cough>, <sniffle>, <groan>, <yawn>, <gasp> New in this model: <moans>, <panting>, <grunting>, <gagging sounds>, <chokeing>, <kissing noises>

Speaker name: baddy Framework: Safetensors (LLaMA) Status: Early preview; training still underway

🔗 Links

—Model files & versions: xet
—Discussion & bug reports: Discord server
—Original author: MrDragonFox

🚀 Usage (Example)

1.Load the *.GGUF file into LMStudio.
2.```bash pip install RealtimeTTS[orpheus]

3. Play TTS:

from RealtimeTTS import TextToAudioStream, OrpheusEngine

engine = OrpheusEngine(model="morpheus3b-1base") # or: engine = OrpheusEngine(model="orpheus3b-1basegguf@q4km") stream = TextToAudioStream(engine) engine.set_voice("baddy")

stream.feed("Mmm <moans>... that feels so good <groan>") stream.play()


---

## ⚖️ License

This model is released under **Creative Commons Attribution‑NonCommercial 4.0 International** (CC‑BY‑NC‑4.0). That means:

- **NonCommercial**: You can use, convert, and share this model for **non‑commercial** purposes only.  
- **Attribution**: You must credit **MrDragonFox**, include the license link, and note any changes you made.  
- **No extra restrictions**: Don’t apply paywalls, DRM, or additional terms.


---

## ⚠️ Disclaimer

- **No warranties**—use at your own risk.  
- Still under development; results may vary.  
- Please report bugs or suggestions on Discord.