erew123
d593bfe52e
Gituhub check on alltalkbeta branch on start
2024-11-05 07:57:05 +00:00
erew123
a8ed41a53b
text correction
2024-11-05 00:04:43 +00:00
erew123
0c9034c1f3
Docker bits
...
Update to gradio interface to be able to set the API address when used within docker.
2024-10-27 01:35:46 +01:00
erew123
f4590d5245
quieten gradio
2024-10-16 07:55:49 +01:00
erew123
37941ab114
Links to WIKI on splashscreen
2024-10-15 07:52:08 +01:00
erew123
a8311005aa
Better handling of tts_engines.json in corrupt/missing scenario
2024-10-02 00:19:37 +01:00
GenericMale
24e6076b40
fix: use sys.executable for subprocess calls
2024-09-13 19:10:52 +02:00
erew123
5257497b57
Notes/warning on docker like environments
2024-07-27 09:17:20 +01:00
erew123
0f26ca4bbf
API address changes apply correctly
2024-07-13 21:49:37 +01:00
erew123
84312bb6b4
RVC Pitch on API
...
adds RVC pitch to the API and generate screen.
Still need to update TGWUI, SillyTavern Extensions along with documentation.
2024-06-17 11:42:54 +01:00
erew123
6f4bec7ab2
Extended TTS generation timeout in Gradio
...
extended the timeout to await a TTS generation response, just to help with Google colab
2024-06-13 12:21:08 +01:00
erew123
037d774f2c
Update re Google Colab/DeepSpeed compile
...
DeepSpeed needs to compile the first time it loads in and a longer wait time is required for the 1st model load with DeepSpeed
2024-06-12 17:13:18 +01:00
erew123
465afd57c8
Accordion on the main Generate screen
2024-06-12 15:35:25 +01:00
erew123
7fc89885eb
Update to deal with TGWUI loading.
2024-06-12 14:04:17 +01:00
erew123
411b93f55c
Prep for Google Colab
2024-06-11 10:19:00 +01:00
erew123
e86109aa14
Gradio over LAN access
2024-06-10 10:31:38 +01:00
erew123
98a74e9625
Add files via upload
2024-06-06 21:12:17 +01:00
erew123
9e45aded81
Delete script.py
2024-06-06 15:27:22 +01:00
erew123
2c7feb31e5
Add files via upload
2024-04-01 12:34:09 +01:00
erew123
cead53a808
Config file checker & clean start-up
...
Cleaned up the start-up screen & added mini diags
Added a config file updater that can be used to add/remove things from the confignew.json file if ever needed.
2024-04-01 12:28:32 +01:00
erew123
51fa4ce9e9
Cleaner Start-up & mini diags
...
Updated various bits of code to clean up the AllTalk start-up messages.
2024-04-01 10:48:36 +01:00
erew123
a075495a0a
Large Update
...
TTS Generator - Various interface bugs & filtering options cleaned up.
TTS Generator - TTSDiff now scans generated text and TTS for errors.
TTS Generator - TTSSRT now creates subtitle files for video production e.g. a Youtube video.
Finetune - Now uses a customised tokenizer to deal with Japanese.
Finetune - Pre flight check and warning messages.
Finetune - Extra documentation and warnings.
Entire file structure has been re-organised to simplify management and future changes.
Documentation (built in and Github) has been rewritten/tidied up.
Requirements files have been cleaned up and simplified.
ATsetup has been re-written as necessary with additional options.
DeepSpeed moved up to version 14.
Standalone Application moved to PyTorch 2.2.1.
Nvidia CUDA Toolkit installation is NO LONGER needed (other than to compile DeepSpeed on Linux)
Tested on Linux and Windows.
2024-03-28 21:49:33 +00:00
erew123
969b4e3f46
Text-gen-webui - SD Image filtering
...
AllTalk will now strip any image from TTS and re-add the image data after TTS.
This is so that when used with Stable Diffusion Image generation within Text-generation-webui, AllTalk isnt trying to generate the Image data as TTS.
2024-03-11 11:22:50 +00:00
erew123
015b9033ec
Additional updates re chinese
...
CJK Symbols and Punctuation range u3000 > u303F
2024-02-21 20:58:57 +00:00
erew123
7f261bb5e9
Attempt to allow Chinese character set through
2024-02-21 12:24:11 +00:00
erew123
00b93cfe1b
explicit allowance for ć, ś, ń, ł etc
2024-02-07 12:44:42 +00:00
Josh XT
ec1d0e8c5d
Check if running in docker
2024-01-22 19:26:23 -05:00
Josh XT
12bf008b3f
Run back end without subprocess
2024-01-22 19:15:54 -05:00
erew123
7010369966
Added startup_wait_time to top of script
...
Making it simple for people to adjust the allowed start-up time
2024-01-21 12:20:29 +00:00
erew123
a9d95fc563
Update script.py
2024-01-18 14:15:34 +00:00
S95Sedan
cefd1e045b
Temperature and Repetition_penalty modification
...
Modified script.py to enable temperature and repetition_penalty to be parsed and tts_server.py to recieve those variables.
2024-01-15 21:51:00 +01:00
erew123
11c70c7432
Tidied console messages
2024-01-13 19:03:26 +00:00
erew123
a50d5a5028
Merge branch 'dev' into patch-1
2024-01-12 13:51:17 +00:00
erew123
d4a04096c8
Made Server address more visible on startup
2024-01-10 18:28:55 +00:00
erew123
e9d9f54de6
Update script.py
2024-01-10 18:10:42 +00:00
S95Sedan
840889ac9a
Update script.py
...
- Changed non_quoted_text_is_gr from "Char" to "Character"
2024-01-10 16:08:51 +01:00
S95Sedan
d3e061b127
Update script.py
...
- GUI overhaul/cleanup.
- Temperature and Repetition penalty in GUI (disabled) but not yet parsed to API
2024-01-10 15:35:13 +01:00
erew123
2c14847708
Update script.py
...
added Hungarian characters
2024-01-05 13:24:20 +00:00
erew123
67dcc411ad
Update script.py
...
Extend allowed characters, additional European & Cyrillic characters
2024-01-04 12:13:38 +00:00
erew123
1893d1a130
remove unused style.css file
2024-01-01 19:55:38 +00:00
erew123
2dd303f53c
Add files via upload
2024-01-01 18:10:14 +00:00
erew123
5ab7463f35
More narrator shenanigans
2023-12-31 21:35:23 +00:00
erew123
2f689f0438
Model loader for Finetuned models
...
Adds a detection routine and additional loader for a finetuned model.
Model has to be in /models/trainedmodel/
2023-12-29 23:15:15 +00:00
erew123
a094d4f9da
Completed autoplay at command line
...
Added additional requirement.
Lowered the repetition on the start-up warning when its taking a while for the model to load.
2023-12-29 20:31:49 +00:00
erew123
3cd22081f4
Update script.py
2023-12-28 21:05:59 +00:00
erew123
acc457436a
updated narrator splitting function
...
Improved over what was before.
Still more work to do in future though.
2023-12-28 18:39:01 +00:00
erew123
a34cbfdd55
Made Settings link more visble
...
Updated the visibility of the settings & documentation page within Text-gen-webui interface.
Minor built in documentation update.
2023-12-27 06:43:28 +00:00
erew123
5bed68a963
minor update to standard voice naming.
2023-12-25 21:53:40 +00:00
erew123
dc9d343115
Update uuid to avoid possible race condition
...
file naming on short sentences could possibly have a race condition. set uuid as opposed to timestamp to avoid this outcome.
2023-12-25 21:09:39 +00:00
erew123
f2119aa0f7
Merge pull request #14 from erew123/dev
...
New Finetuning of your models
New API endpoint
Full documentation (online and built in)
A couple of minor file updates.
Small bug fix on file generation in instruct mode with no character name available (thanks to @danielwburch)
2023-12-24 13:10:18 +00:00
erew123