Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
Pendrokar
/
xVASynth-TTS
like
64
Running
on
CPU Upgrade
App
Files
Files
Community
5
a0a523d
xVASynth-TTS
/
app.py
Commit History
çomment out symlink
a0a523d
Pendrokar
commited on
Feb 13
symlink: target is directory
0df5421
Pendrokar
commited on
Feb 13
symlink to deepmoji model
dee59bd
Pendrokar
commited on
Feb 13
run_deepmoji
6115840
Pendrokar
commited on
Feb 13
comment out response data
beb87c6
Pendrokar
commited on
Feb 13
base_speaker_embs from voice model JSON; Web response.text
044fea4
Pendrokar
commited on
Feb 13
xVASynth synthesize return JSON
dcbacca
Pendrokar
commited on
Feb 13
60 second xvaserver Web request timeouts
49e4ff0
Pendrokar
commited on
Feb 13
language & voice reorder
0191adb
Pendrokar
commited on
Feb 13
remove deepmoji restrictions
7fa8c00
Pendrokar
commited on
Feb 12
skip deepmoji model load
2b57de9
Pendrokar
commited on
Feb 12
default voice value fix
dfbba35
Pendrokar
commited on
Feb 12
indent fix
a4ca82b
Pendrokar
commited on
Feb 12
emotional sliders
83ebf46
Pendrokar
commited on
Feb 12
more human readable voice names
10cf936
Pendrokar
commited on
Feb 12
DeepMoji xVASynth Plugin
e1c08c5
Pendrokar
commited on
Feb 12
hide clear button
5df5032
Pendrokar
commited on
Feb 12
comment out default text switch
f829455
Pendrokar
commited on
Feb 12
country flags; default text in lang
a1d10f4
Pendrokar
commited on
Feb 12
radio defaults
b1e470d
Pendrokar
commited on
Feb 12
language switch
3c34d6c
Pendrokar
commited on
Feb 12
espeak-ng Debian package
91b12d7
Pendrokar
commited on
Feb 12
comma typo
e925b78
Pendrokar
commited on
Feb 12
Radio switch voice model.
9366d4b
Pendrokar
commited on
Feb 12
cached models seem already linked
e494712
Pendrokar
commited on
Feb 12
hf models path fix; max_lines
79e5c13
Pendrokar
commited on
Feb 12
move all nvidia_hifi models
f2cf91b
Pendrokar
commited on
Feb 12
load default model only on startup
2a8b22c
Pendrokar
commited on
Feb 11
example caching breaks Space
8314260
Pendrokar
commited on
Feb 11
Do not cache examples.
85c9f67
Pendrokar
commited on
Feb 11
examples
81f118e
Pendrokar
commited on
Feb 11
fixed model_name var
bbca100
Pendrokar
commited on
Feb 11
model_name var relocated
5f9fada
Pendrokar
commited on
Feb 11
import huggingface_hub
e28791b
Pendrokar
commited on
Feb 11
manual model download
19b56c2
Pendrokar
commited on
Feb 11
Load model only on gen
7d90a74
Pendrokar
commited on
Feb 11
audio filepath
df59219
Pendrokar
commited on
Feb 11
return filepath to gradio
ad6d20f
Pendrokar
commited on
Feb 11
change generated file location
6299b6a
Pendrokar
commited on
Feb 11
return audio bytedata to gradio
de7f50d
Pendrokar
commited on
Feb 11
reload model before synthesis
1cd6967
Pendrokar
commited on
Feb 11
base_embs as str
f14288a
Pendrokar
commited on
Feb 11
hard coded base speaker embeds
72fdcb1
Pendrokar
commited on
Feb 11
ffmpeg; abs path to xvaserver
e283de7
Pendrokar
commited on
Feb 11
xvaserver cwd to itself
ea64d8e
Pendrokar
commited on
Feb 11
verbose xvaserver startup
e1a50fc
Pendrokar
commited on
Feb 11
relocate server.py
3a99466
Pendrokar
commited on
Feb 11
full path to voice model
ba2ad2a
Pendrokar
commited on
Feb 11
catch model raised except
a65b632
Pendrokar
commited on
Feb 11
load default model
50319fb
Pendrokar
commited on
Feb 11
Previous
1
2
Next