Downloads · 30 days
42
0% of all-time downloads
orpheus-urdu-tts
mahwizzzz/orpheus-urdu-tts
orpheus-urdu-tts is a text-to-speech model from mahwizzzz. Use it when you need text read aloud. The card lists the license as mit.
Samle generated audio <audio controls src="https://cdn-uploads.huggingface.co/production/uploads/62c5a943b4d97e47fd7cfaf7/mP5dWqQfIYdcYOkhARij7.wav"</audio
All-time downloads
876K
Public
Parameters
3.3B
6.6 GB on disk
Likes
12
Public
Repo makeup
Click a slice to open those files.
.safetensors6.6 GB · 100%
At a glance
- Task
- Text-to-Speech
- License
- mit
- Model type
- llama
- Access
- Public
- Created
- Apr 5, 2025
- Updated
- Nov 4, 2025
- SHA
- 5b75ef60
Base models
Datasets
Model card
From the Hugging Face model README
Orpheus Urdu (16 bit)
Samle generated audio <audio controls src="https://cdn-uploads.huggingface.co/production/uploads/62c5a943b4d97e47fd7cfaf7/mP5dWqQfIYdcYOkhARij7.wav"></audio>
Model Description
The Orpheus Urdu TTS model is a fine-tuned version of the Orpheus 3B text-to-speech model specifically adapted for Urdu language. This experimental model not recommended for production use this was trained on the mahwizzzz/UAT dataset, which contains 20.4k audio samples split from train. This fine-tuning was performed for 10 epochs on a single RTX 4090.
Intended Use
This model can be used for generating Urdu speech from text. It is ideal for experimenting with TTS systems for Urdu, particularly for audiobooks, conversational AI, or speech synthesis tasks.
Model Training
- Dataset:
mahwizzzz/UAT(20.4k audiobook audio samples) - Training Epochs: 10 epochs
- Hardware: RTX 4090
Model Usage
- Task
- Text-to-Speech
- Type
- llama
- License
- mit
- Languages
- ur
- Created
- Apr 5, 2025
- Updated
- Nov 4, 2025