Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens
Paper
•
2503.01710
•
Published
•
3
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's activity
some questions
3
#11 opened 14 days ago
by
ZBW
AI model traning - Commercial
1
#13 opened 9 days ago
by
florent-martineau
lmxue
authored
a
paper
1 day ago
Emilia-YODAS
3
#12 opened 14 days ago
by
mrfakename
yuantuo666
updated
a
dataset
14 days ago
some questions
3
#11 opened 14 days ago
by
ZBW
Emilia-YODAS
3
#12 opened 14 days ago
by
mrfakename
HarryHe
updated
a
dataset
14 days ago
zjc1617018
updated
a
model
15 days ago
Upload metis_vc.safetensors
#9 opened 15 days ago
by
zjc1617018
Upload metis_l2s.safetensors
#8 opened 15 days ago
by
zjc1617018
Upload metis_l2s.safetensors
#7 opened 15 days ago
by
zjc1617018
200k hours Emilia-large
2
#9 opened about 1 month ago
by
clementruhm
Release Emilia-YODAS
1
#10 opened 22 days ago
by
yuantuo666
wli3221134
updated
a
Space
16 days ago
Upload 2 files
#4 opened 16 days ago
by
zjc1617018
Upload model.safetensors
#6 opened 16 days ago
by
zjc1617018
Upload 2 files
#5 opened 16 days ago
by
zjc1617018
Upload model.safetensors
#6 opened 16 days ago
by
zjc1617018
Upload 2 files
#5 opened 16 days ago
by
zjc1617018