amphion/anyaccomp
Updated
•
14
•
7
AI & ML interests
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.
Recent Activity
View all activity
amphion/dualcodec
Audio-to-Audio
•
Updated
•
3
amphion/INTP
Updated
amphion/TaDiCodec
Audio-to-Audio
•
0.5B
•
Updated
•
51
•
27
amphion/TaDiCodec-TTS-MGM
Text-to-Speech
•
0.6B
•
Updated
•
17
•
3
amphion/TaDiCodec-TTS-AR-Qwen2.5-0.5B
Text-to-Speech
•
0.5B
•
Updated
•
17
•
8
amphion/TaDiCodec-TTS-AR-Qwen2.5-3B
Text-to-Speech
•
3B
•
Updated
•
9
•
5
amphion/dualcodec-tts
Updated
•
4
amphion/Metis
Text-to-Speech
•
Updated
•
12
•
25
amphion/Vevo
Text-to-Speech
•
Updated
•
19
•
41
amphion/MaskGCT
Text-to-Speech
•
Updated
•
3.48k
•
300
amphion/Vevo1.5
Updated
•
15
•
18
amphion/valle
Updated
•
4
•
1
amphion/naturalspeech3_facodec
Updated
•
87
amphion/vits_ljspeech
Updated
amphion/fastspeech2_ljspeech
Updated
amphion/hifigan_ljspeech
Updated
amphion/vits_hifitts
Updated
amphion/valle_librilight_6k
Updated
•
1
amphion/valle_libritts
Updated
•
4
amphion/diffwave
Updated
amphion/BigVGAN_singing_bigdata
Updated
•
2
amphion/hifigan_speech_bigdata
Updated
•
4
amphion/singing_voice_conversion
Updated
•
29
amphion/naturalspeech2_libritts
Updated
•
8
amphion/text_to_audio
Updated
•
10