Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.
Repositories
Plachtaa repositories
Plachtaa/Amphion-1Python
(3 stars) (1 fork) (0 indexed issues) (0 open good first issues)
speaker-disentangled speech linguistic content quantizer
(26 stars) (5 forks) (0 indexed issues) (0 open good first issues)
Plachtaa/FAcodecPython
Training code for FAcodec presented in NaturalSpeech3
(244 stars) (21 forks) (0 indexed issues) (0 open good first issues)
(0 stars) (2 forks) (0 indexed issues) (0 open good first issues)
Plachtaa/seed-vcPython
zero-shot voice conversion & singing voice conversion, with real-time support
(3,887 stars) (532 forks) (0 indexed issues) (0 open good first issues)
Plachtaa/StreamVoiceAnonPython
[ICASSP'26] Real-time streaming voice anonymization & voice conversion
(92 stars) (9 forks) (0 indexed issues) (0 open good first issues)
Plachtaa/VALL-E-XPython
An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/
(7,931 stars) (781 forks) (6 indexed issues) (6 open good first issues)
This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion
(5,012 stars) (727 forks) (0 indexed issues) (0 open good first issues)