Tony Ribeiro
b5fcde2611
Added RVC request function to allow upload models from ST. Added parameter --max-content-length=X (Mb) to set server max request data size accordingly if needed.
2023-08-17 04:44:49 +02:00
Tony Ribeiro
185fc1334f
Added parameter --rvc-save-file to save last rvc input/output audio file into data/tmp. For research purpose and easy sharing of TTS/RVC sample files
2023-08-17 01:43:13 +02:00
Tony Ribeiro
4992ce0bd3
Added Coqui STT module request function for listing local models and generating tts using it.
2023-08-16 19:20:55 +02:00
Tony Ribeiro
da6bbf879e
Added RVC module function to fix models folder organisation (if possible)
2023-08-16 16:38:59 +02:00
Tony Ribeiro
fd6ef64d80
Updated RVC voice conversion function to handle new parameters
2023-08-15 21:16:59 +02:00
Tony Ribeiro
75d48a9638
Added argument '--coqui-models=model1,model2' allowing to download given coqui-api models and keep the last one loaded ready for first tts request.
2023-08-15 17:20:23 +02:00
Tony Ribeiro
84ed0f5de3
remove debug message
2023-08-15 15:43:58 +02:00
Tony Ribeiro
a403eb0247
Corrected coqui gpu option to be actually taken into account ^^
2023-08-15 15:43:00 +02:00
Tony Ribeiro
c800eae3e8
Cleanup remaining old coqui implementation
2023-08-14 05:32:34 +02:00
Tony Ribeiro
46fecb5b48
Merge branch 'neo' of https://github.com/Tony-sama/SillyTavern-extras into neo
2023-08-14 04:04:55 +02:00
Tony Ribeiro
a440177f25
reduced coqui api call to minimum, added model download
2023-08-14 04:04:46 +02:00
Tony Ribeiro
f87ac34928
Merge branch 'SillyTavern:neo' into neo
2023-08-14 04:01:46 +02:00
Cohee
53020b34f7
#120 Fix coqui module overwriting system function
2023-08-13 18:53:03 +03:00
Tony Ribeiro
db63c58c30
Added missing route to populate ST coqui UI settings and download/check models of coqui api.
2023-08-13 02:19:47 +02:00
Tony Ribeiro
1389d3806d
Started refactoring of Coqui-tts extension.
2023-08-12 06:06:55 +02:00
joe
712e5508da
Clean up and prevent double load
2023-08-11 09:15:27 +09:00
joe
7ad0bb5598
live2d -> talkinghead name change
2023-08-11 06:50:59 +09:00
Tony Ribeiro
60a8e5c9c6
Add monkey patched fairseq package to run on python 3.11 (what is needed for our use of RVC at least)
2023-08-10 02:58:52 +02:00
Tony Ribeiro
0d00b5fdd0
Add module managing RVC extension to convert audio sent by ST using voice model
2023-08-09 03:38:13 +02:00
Cohee
9a650c4cec
Merge pull request #111 from SillyTavern/main
...
Remove persist call for chroma
2023-08-08 17:44:12 +03:00
Cohee
5ed3013e45
Remove persist call for chroma
2023-08-08 17:43:15 +03:00
Cohee
36e6bfaf44
Merge branch 'main' into neo
2023-08-05 15:29:50 +03:00
Cohee
0c09107dd4
Add Python 3.11 recommendation nudge
2023-08-05 15:06:24 +03:00
joe
dbc7e07c0a
Emotion Animation changes Staging
2023-08-05 17:02:53 +09:00
joe
5f4671f8e8
Coqui TTS Cpu/Gpu Flag Fix
2023-08-04 16:24:50 +09:00
joe
d1e2efedba
Perfomance Increase and cleanup
2023-08-04 08:32:02 +09:00
joe
05a12822a7
WIP Updates to CTRL C hang up
2023-08-02 09:58:22 +09:00
Cohee
bfdf62765d
Load live2d by posting a file
2023-08-01 23:57:32 +03:00
joe
ef8e0493e8
added live2d Arg for gpu or cpu mode
2023-08-01 07:32:32 +09:00
Cohee
38b6403ca1
Port chromadb update from neo
2023-07-31 22:14:42 +03:00
Cohee
d47cb539ad
Merge pull request #96 from Tony-sama/neo
...
Restored speech recognition streaming mode as an independant module.
2023-07-31 20:42:40 +03:00
Tony Ribeiro
912c4335c2
Restored speech recognition streaming mode as an independant module. Perform audio recording using mic on server side, detect voice start/end with vosk and transcript with whisper.
2023-07-31 18:50:44 +02:00
donlinglok
abecb1ca5b
Update server.py
2023-07-31 22:05:26 +08:00
donlinglok
c19e6d3881
Update server.py
2023-07-31 22:02:31 +08:00
donlinglok
17d622d7bf
Update server.py
2023-07-31 21:56:03 +08:00
donlinglok
1dce09959e
Update server.py for new chroma
2023-07-31 21:38:02 +08:00
joe
3673766580
Live2d Init
2023-07-31 08:35:30 +09:00
SillyLossy
3975a3a179
Fix Chromadb client creation
2023-07-30 01:19:39 +03:00
Tony Ribeiro
d528c5e5ad
merge speech recoginition module with neo branch.
2023-07-27 20:29:17 +02:00
SillyLossy
9b1e3d1250
Add coqui model preload
2023-07-26 22:49:44 +03:00
Cohee
b5d35f470f
Migrate coqui module to neo branch
2023-07-25 17:08:05 +03:00
Cohee
5cd40e0520
Fix coqui TTS module
2023-07-25 12:46:17 +03:00
SillyLossy
0b25aff3e1
Hardcode test.wav path
2023-07-09 21:46:45 +03:00
50h100a
61bf91c182
Enhance logging.
2023-07-08 04:36:33 -04:00
50h100a
57fc3485d9
Don't scream when accessing an empty/missing collection.
...
(it's usually expected behavior)
2023-07-08 04:30:57 -04:00
Blueprint Coding
57be2e167a
Silero TTS Fix for "File already exists"
...
Added fix for Silero not working as new files were unable to be created if one already existed.
2023-07-07 13:30:14 -06:00
BlipRanger
4ada6d3c7f
Minimum error handling for bad chroma requests
2023-07-05 22:49:08 -04:00
Blueprint Coding
3227e1c196
Updated Silero TTS to be compatible with STSL
...
Had to add absolute pathing for SILERO_SAMPLES_PATH, SILERO_SAMPLE_TEXT, & audio to set the extras directory based on the parent folder. Because of STSL dynamic install locations they were getting placed in the STSL folder instead of extras.
Should not effect regular launching via python.
2023-07-04 13:05:19 -06:00
YellowRoseCx
b17211bafa
fix cpu mode
...
adds back "and not args.cpu" to device_string otherwise cpu mode will never trigger if a cuda device is installed in the machine
2023-06-30 00:13:20 -05:00
majick
dea4254e01
Fix: inverted sense bug with cuda sd float32
...
Inverting the use of float16 with SD on cuda was introduced with my MPS
hack. Fixed.
Also, make the MPS changes more consistent with cuda_device, since we
don't need a hardcoded value any more.
2023-06-28 14:19:59 -07:00
