kromskii2/alltalk_tts
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
947 Commits 2 Branches 23 Tags
a495c0a2397bae95100b0aedf5039c6ccf2cc9e4
Commit Graph
86 Commits
Author SHA1 Message Date
erew123 f3b44424ef Update for word add-in 2024-01-03 01:28:56 +00:00
erew123 2dd303f53c Add files via upload 2024-01-01 18:10:14 +00:00
Ryan 6ef2de2923 Support streaming of model inference to lower time to first token for long passages. Uses the new CoquiTTS inference_stream() function 2024-01-01 00:27:11 -08:00
Ryan 11071b279b Templatize the tts-server HTML for ease of editing 2023-12-31 15:06:39 -08:00
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 221efbddb4 Supports playback at the command line prompt 
Added sounddevice as its currently well supported. Allows playback at the terminal/command prompt. 
Added speakers_xtts.pth to the modeldownload.json as it will be needed for finetuning in future updates of TTS 0.22.0+
 2023-12-29 10:42:35 +00:00
erew123 e81a88938a Completed built-in documentation update 
For the new API endpoints
 2023-12-29 10:11:01 +00:00
erew123 65e257077c 3x new API endpoints 
/api/voices/
/api/previewvoice/
/api/ready/
 2023-12-29 09:56:51 +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 94f5b781cc Update Standalone API - race condition fix 
Applies the same race condition fix for narrator/character that potentially existed, but for the standalone mode API. Will have zero effect for anyone not using the API
 2023-12-27 06:08:10 +00:00
erew123 97f0d6441a Improved links in Documentation 
Added links to the minor bugs/known issues on gthub
 2023-12-26 07:30:30 +00:00
erew123 52a7922e98 Add files via upload 2023-12-25 02:05:05 +00:00
erew123 d26909a1d6 All the updates for Finetuning 
Additional files to download
Updated documentation
Updated requirements files
 2023-12-24 12:32:10 +00:00
erew123 f25d2627cd updated timeout to 80 seconds 
Much older systems with low system ram are taking 70 seconds to start up (so Im told). Ive added an extra 20 seconds onto the 60 seconds for subprocess start-up.

documentation updated too.
 2023-12-21 12:47:53 +00:00
erew123 8f318892c2 New API endpoint 
adds the /api/tts-generation endpoint & documentation.
 2023-12-21 11:32:59 +00:00
erew123 96aef2c1be Updating docs CURL 
Curl command rendered incorrectly in HTML, so corrected
 2023-12-20 01:12:45 +00:00
erew123 efd3a0add3 Documentation & Diagnostics 
Cleaned up the built in documentation. 
Also added diagnostics.py to help with diagnosing anyone's problems.
 2023-12-19 16:33:06 +00:00
erew123 68acd49234 documentation changes 
a few minor updates to docs
 2023-12-17 11:24:23 +00:00
erew123 9306b31c12 Updated Docs & config file 
Had to update a variable due to the latest version of pydantic using a similar variable and causing a potential clash. As such, I have had to use a new configuration file (simplest method). Peoples base settings will be reset on next update. Added a option in the config file for standalone mode output.
 2023-12-17 11:02:32 +00:00
erew123 5b174bab35 pull params correctly into HTML 
Only affects custom IP/ports. No changes otherwise.
 2023-12-17 05:45:51 +00:00
erew123 bcb5832c4c Upgrade to v1.5 
Added:
- new documentation
- demo in the documentation
- extra API endpoints (yet to be documented)
- voice notification on change of model or setting
- DeepSpeed update to v11.x and re-documented
- improved vocab bringing the XTTSv2 model closer to sounding like the sample, with improved pronunciation and intonation.
 2023-12-15 22:07:06 +00:00
erew123 e8dde29d20 Documentation update 
Updated a note in the documentation about correct formatting of RP character greeting cards
 2023-12-13 12:11:28 +00:00
erew123 b7de2988b0 Updated note about clip length 
Turns out the models default config file is setting "max_ref_len": 30, allowing for up to 30 second long voice clips to be used.
 2023-12-13 05:21:38 +00:00
erew123 40b775459e New Narrator Version 
The narrator and filtering has been re-written to vastly improve filtering of text, resulting in less unwanted sounds and better control over narrator/character.
 2023-12-13 04:51:41 +00:00
erew123 fc3bb6f406 Update tts_server.py 
small spelling mistake
 2023-12-11 19:22:41 +00:00
erew123 e4b581a1be Backend access to temp and repetition 
Added the capability to change the default temperature and repetition settings of the model along with writing documentation to explain it all.
 2023-12-11 13:44:12 +00:00
erew123 ee3f5cb853 Applied extra settings to TTS generation 
Pulled some extra settings from the models configuration file to help keep generated speech closer to the sample wav.
 2023-12-11 02:53:51 +00:00
erew123 6ea56eddfa Allow standalone running 
Added logic to allow script to be run as a standalone if required (outside of Text-generation-webui)
Corrected spelling mistake in documentation.
 2023-12-10 20:02:36 +00:00
erew123 5124c6c6b3 Test around cuda for non-cuda users 
- made logic for model loading on non-cuda systems
- split requirements files into nvidia and other
- updated other files as necessary
 2023-12-10 10:48:48 +00:00
erew123 9927b51622 Populate settings with wav voices 2023-12-10 09:49:07 +00:00
erew123 00c5d5abac Narrator included 2023-12-09 19:14:54 +00:00
erew123 3f844932eb Add files via upload 2023-12-08 16:29:59 +00:00
erew123 1eb0d0a103 Spelling corrections 2023-12-08 15:43:39 +00:00
erew123 ce11e4846e Branding Change 2023-12-08 14:54:45 +00:00
erew123 f891d1330e Initial Build 2023-12-08 09:35:53 +00:00