Downloads · 30 days
8
15% of all-time downloads
openaudio-s1-mini-twi
prince4332/openaudio-s1-mini-twi
openaudio-s1-mini-twi is a text-to-speech model from prince4332. Use it when you need text read aloud. The card lists the license as apache-2.0.
Fine-tuned from fishaudio/openaudio-s1-mini on an Asante Twi speech corpus using LoRA (r=8, alpha=16).
All-time downloads
55
Public
Repo size
3.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth3.4 GB · 100%
At a glance
- Task
- Text-to-Speech
- License
- apache-2.0
- Model type
- dual_ar
- Access
- Public
- Created
- Jun 5, 2026
- Updated
- Jun 5, 2026
- SHA
- fbf91882
Base models
Model card
From the Hugging Face model README
OpenAudio S1 Mini — Asante Twi Fine-tune
Fine-tuned from fishaudio/openaudio-s1-mini on an Asante Twi speech corpus using LoRA (r=8, alpha=16).
Usage
Load with fish-speech and pass a reference audio at inference time to control speaker timbre.
Files
| File | Description |
|---|---|
model.pth | Merged LLaMA weights (base + LoRA) |
config.json | Model config |
- Task
- Text-to-Speech
- Type
- dual_ar
- License
- apache-2.0
- Languages
- tw
- Created
- Jun 5, 2026
- Updated
- Jun 5, 2026