Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens
Paper
•
2503.01710
•
Published
•
5
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
samples of another language are mixed in a webdataset
1
#14 opened 19 days ago
by
sjchung
some questions
3
#11 opened about 1 month ago
by
ZBW
AI model traning - Commercial
1
#13 opened 28 days ago
by
florent-martineau
lmxue
authored
a
paper
20 days ago
Emilia-YODAS
3
#12 opened about 1 month ago
by
mrfakename
yuantuo666
updated
a
dataset
about 1 month ago
some questions
3
#11 opened about 1 month ago
by
ZBW
Emilia-YODAS
3
#12 opened about 1 month ago
by
mrfakename
HarryHe
updated
a
dataset
about 1 month ago
zjc1617018
updated
a
model
about 1 month ago
Upload metis_vc.safetensors
#9 opened about 1 month ago
by
zjc1617018
Upload metis_l2s.safetensors
#8 opened about 1 month ago
by
zjc1617018
Upload metis_l2s.safetensors
#7 opened about 1 month ago
by
zjc1617018
200k hours Emilia-large
2
#9 opened 2 months ago
by
clementruhm
Release Emilia-YODAS
1
#10 opened about 1 month ago
by
yuantuo666
lmxue
authored
a
paper
about 1 month ago
Hecheng0625
authored
a
paper
2 months ago
jiaqili3
authored
a
paper
2 months ago
HarryHe
authored
2
papers
2 months ago