Downloads · 30 days
21
1% of all-time downloads
orpheus-tj-early
re-skill/orpheus-tj-early
orpheus-tj-early is a text-to-speech model from re-skill. Use it when you need text read aloud. It is set up for transformers. The card lists the license as apache-2.0.
25/07/2025 – We are releasing our early checkpoint of 3B Orpheus TTS trained only 35 hours of audio data.
All-time downloads
2.1K
Public
Parameters
3.3B
52.8 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors13.2 GB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- transformers
- License
- apache-2.0
- Model type
- llama
- Access
- Public
- Created
- Jun 16, 2025
- Updated
- Jun 25, 2025
- SHA
- ccce0609
Base models
Model card
From the Hugging Face model README
Orpheus 3B 0.1 Finetuned on Tajik
25/07/2025 – We are releasing our early checkpoint of 3B Orpheus TTS trained only 35 hours of audio data.
Orpheus TTS is a state-of-the-art, Llama-based Speech-LLM designed for high-quality, empathetic text-to-speech generation. This model has been finetuned to deliver human-level speech synthesis, achieving exceptional clarity, expressiveness, and real-time streaming performances.
Usage
Check out our Colab (link to Colab) to run locally on your Mac check (MLX version)
Model Misuse
Do not use our models for impersonation without consent, misinformation or deception (including fake news or fraudulent calls), or any illegal or harmful activity. By using this model, you agree to follow all applicable laws and ethical guidelines. We disclaim responsibility for any use.
- Task
- Text-to-Speech
- Library
- transformers
- Type
- llama
- License
- apache-2.0
- Languages
- tg
- Created
- Jun 16, 2025
- Updated
- Jun 25, 2025