Downloads · 30 days
20
1% of all-time downloads
kotoba-speech-v0.1
kotoba-tech/kotoba-speech-v0.1
kotoba-speech-v0.1 is a text-to-speech model from kotoba-tech. Use it when you need text read aloud. It is set up for transformers. The card lists the license as apache-2.0.
Kotoba-Speech v0.1 is a 1.2B Transformer-based speech generative model. It supports the following properties: 1. Fluent text-to-speech generation in Japanese 2. One-shot voice cloning through speech prompt
All-time downloads
1.7K
Public
Repo size
10 GB
Likes
17
Public
Repo makeup
Click a slice to open those files.
.pt5 GB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Mar 14, 2024
- Updated
- Apr 17, 2024
- SHA
- c8f3ce36
Model card
From the Hugging Face model README
Kotoba-Speech-v0.1
Kotoba-Speech v0.1 is a 1.2B Transformer-based speech generative model. It supports the following properties:
- Fluent text-to-speech generation in Japanese
- One-shot voice cloning through speech prompt
Usage
Plesae check out our HF Spaces demo.
Model Details
- Model type: Our model is end-to-end transformers.
- Language(s): Japanese
- Library: We'll releasde our training code soon. Inference and model code are largely adopted from metavoice.
Acknowledgements
- We thank meta-voice for opensourcing their code.
License
Apache License Version 2.0, January 2004
- Task
- Text-to-Speech
- Library
- transformers
- License
- apache-2.0
- Languages
- ja
- Created
- Mar 14, 2024
- Updated
- Apr 17, 2024