Spaces:
Running
on
T4
Running
on
T4
Commit History
xtts v2 with silence fix
96324d6
use v1.1 model for now
e5753d7
Update app.py
d559922
add korean and hungarian and v2
595fb7a
Update app.py
6d2da72
Update app.py
18b8c5f
Use xtts-streaming for generation
156829e
Update app.py
f7c2b84
show_api=True
ccaf952
Update app.py
6550ebd
Update app.py
4e13633
say we collect error data only
8d2ef4c
will upload non-recoverable errors so we can debug
48423a0
decoder="ne_hifigan" try
23f5658
Update app.py
764a0de
Update app.py
285150b
Update app.py
08f0cf6
japanese example
17283f5
japanese will be opened up after tts update
5edb992
add japanese
3666957
add japanese
4584388
xtts_v1.1
39fe02d
add links
1db3815
Use inference via python directly
f81d4f2
enable autoplay
d8cc0b4
Update app.py
869b784
Update app.py
7820d65
fix ordering of tts_to_file
78b68ae
Update app.py
8fbd19a
Update app.py
a01dadc
Preferred reference duration is 6 seconds not 3
12438dd
make voice cleaner optional
3b69bc5
Update app.py
4281c8c
remove denoiser, apply trim silence and speech detect loudness
d0834d6
remove lowpass_highpass filter
00e2817
Update app.py
9115bac
fix filter
bebf084
after processing should generate unique filename for microphone
5b0db06
Update app.py
f05e79d
use ffmpeg to denoise microphone input
0db6209
ggoknar
commited on