kromskii2/alltalk_tts
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
885 Commits 2 Branches 23 Tags
7909327f5193adcf91571eaa0890ede30b8907a9
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
erew123 7909327f51 fix missing model logic 2024-11-24 06:18:24 +00:00
erew123 03c9d810ff fix missing model logic 2024-11-24 06:17:53 +00:00
erew123 e0621a97d6 Added JSON latents creation 
- System automatically creates `.json` latent files alongside voice samples
    - Latents are voice characteristics extracted from audio
    - Generated on first use of a voice file
    - Stored next to original audio (e.g., `broadcaster_male.wav` → `broadcaster_male.json`)
    - Improves generation speed for subsequent uses
    - No manual management needed
 2024-11-24 05:56:54 +00:00
erew123 11a116f54c small note 2024-11-24 05:01:19 +00:00
erew123 82894fe1ff tts-gen adds whisper version support 2024-11-24 02:20:00 +00:00
erew123 44d450a4b7 TTS-Diff Adds whisper version support 2024-11-24 02:19:11 +00:00
erew123 1ed7b860c5 XTTS Latents & Multi-voice folders 2024-11-22 19:44:50 +00:00
erew123 87cb4e2754 Correct Finetune CSS 2024-11-22 19:41:35 +00:00
erew123 bc3d9a6d4a Confirm upload vits 2024-11-22 19:31:39 +00:00
erew123 6d50941146 Update basediagnostics.log to current build 2024-11-22 19:30:19 +00:00
erew123 2edfd4f517 updated help content 2024-11-22 19:25:32 +00:00
erew123 ddbe382e67 scipy & plotly added 2024-11-22 19:24:56 +00:00
erew123 b8560779d1 scipy & plotly 2024-11-22 19:23:41 +00:00
erew123 acde395350 Update atsetup.bat Gradio 4.44.1 2024-11-22 19:20:42 +00:00
erew123 8ea93d35cf Update atsetup.sh Gradio 4.44.1 2024-11-22 19:20:08 +00:00
erew123 925c73af63 Update help_content.py 2024-11-22 08:14:58 +00:00
erew123 73d3bc7495 Upload of NEW script.py & tts_server.py 
Fully re-worked script.py and tts_server.py

### THIS IS THE BIG CHANGE COMMIT FOR V2 ###
 2024-11-22 07:36:02 +00:00
erew123 85f204c3f1 Updates to Piper 2024-11-22 07:33:28 +00:00
erew123 1a5c10710d Updates to TTS Engines 2024-11-22 07:32:38 +00:00
erew123 7e73053fd7 Updated TTS Diff 
Uses Whisper now
 2024-11-22 06:59:55 +00:00
erew123 190ccd7551 Update requirements_standalone.txt 2024-11-22 06:59:16 +00:00
erew123 bcfcd1e469 Update requirements_colab.txt 2024-11-22 06:58:57 +00:00
erew123 4556b2b1c7 Delete system/gradio_pages/api_documentation.py 
No Longer used
 2024-11-22 06:57:31 +00:00
erew123 0cec908ada Delete system/gradio_pages/alltalk_welcome.py 
No Longer used
 2024-11-22 06:57:20 +00:00
erew123 10368fc5c0 Delete system/gradio_pages/alltalk_generation_help.py 
No Longer used
 2024-11-22 06:57:06 +00:00
erew123 d145da5ca2 Delete system/gradio_pages/alltalk_documentation.py 
No Longer used
 2024-11-22 06:56:46 +00:00
erew123 b6f4731df7 Delete system/gradio_pages/alltalk_about.py 
No Longer used
 2024-11-22 06:56:30 +00:00
erew123 cf3381c512 Updated Help/Welcome screen 2024-11-22 06:54:12 +00:00
erew123 24dc04b167 Delete system/config/at_configupdate.json 2024-11-22 06:53:02 +00:00
erew123 cbe02ff8d1 Delete system/config/at_configdowngrade.json 2024-11-22 06:52:52 +00:00
erew123 37c46a91f3 Delete system/config/AllTalk API Process.png 
No Longer used
 2024-11-22 06:52:31 +00:00
erew123 4190269d29 Delete system/at_sounds directory 
No longer used
 2024-11-22 06:51:58 +00:00
erew123 9e7a785303 Add default_config_path 
Added default_config_path & set debug_narrator = False
 2024-11-20 01:15:10 +00:00
erew123 fff2fac88d Updated config.py 2024-11-20 00:50:19 +00:00
erew123 18b580db04 Delete system/TGWUI Extension directory 
Had to change dir to TGWUI_Extension to support import via script.py
 2024-11-20 00:49:31 +00:00
erew123 c13dd9ddd7 Updated TGWUI Remote Extension 
Updates:
- Fully re-worked
- Behaves as both a remote extension & the TGWUI code for script.py to import
- Added RVC pitch support
- Config will be central OR JSON file depending how the script is run/imported
 2024-11-20 00:48:43 +00:00
erew123 cea89ddb45 Re-work of core system files 
Updated:
- script.py
- tts_server.py
- test_server.py (used to test the AllTalk server endpoints)
 2024-11-20 00:46:02 +00:00
erew123 eea4bbf4da Merge pull request #395 from Paladinium/alltalkbeta_config_refactoring 
Adding config classes and tests
 2024-11-18 22:25:28 +00:00
erew123 8f871a0601 Final Commit to ST 
https://github.com/SillyTavern/SillyTavern/pull/3060
 2024-11-17 12:34:18 +00:00
erew123 ac24e5fc9a Added debugging to Training section 2024-11-17 04:38:46 +00:00
erew123 f8c9c58d67 clarify some language in the help content 2024-11-17 00:00:41 +00:00
erew123 9a2b4309a5 Custom dataset - ensure lang set 
When using custom datasets that are not built within finetune, ensure lang.txt is read correctly.
 2024-11-16 23:51:56 +00:00
erew123 80dd102da8 Fix Dataset Validation when no errors found 
Fixes an issue where the dataframe errors if no transcription errors found.
Added debugging option for dataset validation
 2024-11-16 15:49:41 +00:00
erew123 f938f83131 Update README.md 2024-11-16 05:28:27 +00:00
erew123 6df2b6eeb4 Delete training_metrics.png 2024-11-16 05:10:56 +00:00
erew123 af1cab8676 Moved metrics_logger.py 
moved into trainer_alltalk folder
 2024-11-16 05:10:37 +00:00
erew123 adc9bb8cc6 Lint clean & documentation 
Cleaned finetune lint
Moved documentation out
Moved metrics logger
 2024-11-16 05:09:48 +00:00
erew123 b538564da6 Update to use openai-whisper 2024-11-15 00:40:02 +00:00
erew123 5c4726de96 New Finetune 
added subprocess
 2024-11-15 00:38:43 +00:00
erew123 2e2714548f Update requirements_textgen.txt 2024-11-15 00:34:12 +00:00
erew123 17b9481fff Update requirements_textgen.txt 2024-11-15 00:26:09 +00:00
erew123 6383b1a134 rem faster-whisper add openai-whisper 
Removed:
nvidia-cublas-cu11>=11.11.3.6
nvidia-cudnn-cu11>=9.1.1.17
faster-whisper>=1.0.3

Added:
openai-whisper
 2024-11-15 00:25:34 +00:00
erew123 a9433f23f3 Update README.md 2024-11-15 00:23:12 +00:00
erew123 22f3eb01e5 Update README.md 2024-11-15 00:22:49 +00:00
erew123 1bd8f6aed9 New Finetune for XTTS 
Interface cleaned
Documentation improved & expanded
Dataset generation improved:
- Better VAD detection
- Better debugging/information
- Better editing/managing transcriptions
- Basic audio editing
- Re-transcription on detections of duplicate audio when splitting large files.
- Control over model precision fp16/fp32/mixed
- Migrate to openai-whisper (also saving 1.5GB on installation requirements for cublas)
Testing stage allows you to choose what minimum length audio
Model export exports all audio with text file descriptions of too long/too short
Misc other improvements too numerous to mention
 2024-11-15 00:21:40 +00:00
erew123 9df1065be0 Update README.md 2024-11-11 14:19:16 +00:00
erew123 029e5dd1b9 Update README.md 2024-11-11 14:12:13 +00:00
erew123 4aa4493cc5 Clearer messages commit correction 2024-11-11 11:35:59 +00:00
erew123 5a3a20dcba Clearer message on missing model files 2024-11-11 11:33:40 +00:00
erew123 73c8c71be9 Clearer messages 2024-11-11 11:23:09 +00:00
erew123 80821081fb Update README.md 2024-11-11 05:14:09 +00:00
erew123 20361d4a0c Update README.md 2024-11-11 05:04:25 +00:00
erew123 4d512f4677 Built in Server version selection 2024-11-10 19:42:38 +00:00
erew123 51e0b21682 Improvements Dataset Management & Wav files. 
Logging and console/terminal output may need some work correcting in future,
 2024-11-10 17:25:02 +00:00
erew123 07053f8076 Update README.md 2024-11-09 00:27:29 +00:00
erew123 79e8e49d06 Update README.md 2024-11-09 00:25:05 +00:00
erew123 e7a8fff709 Update README.md 2024-11-09 00:24:34 +00:00
erew123 398de26248 Update script.py 2024-11-08 20:33:59 +00:00
erew123 e0527ca8a3 Update legacy API Saving 2024-11-08 20:33:23 +00:00
erew123 c2e1095bb8 add gradio page section 2024-11-08 20:14:56 +00:00
erew123 03148509e4 Update for Coqui 0.24.3 2024-11-06 01:43:14 +00:00
erew123 bfe14f3524 Update for Coqui 0.24.3 2024-11-06 01:42:08 +00:00
erew123 8536eae276 Update for Coqui 0.24.3 2024-11-06 01:41:39 +00:00
erew123 67693f66e0 Update for Coqui 0.24.3 2024-11-06 01:41:22 +00:00
erew123 590eb23e78 add UNetT import 2024-11-05 10:25:32 +00:00
erew123 1b4e982955 add back setup routine 2024-11-05 10:22:50 +00:00
erew123 5a81e4818b Add support for the E2 model to F5-TTS 2024-11-05 10:19:45 +00:00
erew123 1a5945235d F5-TTS Unload model correct tab 2024-11-05 09:51:50 +00:00
erew123 88c97ea700 Update README.md 2024-11-05 08:04:01 +00:00
erew123 d593bfe52e Gituhub check on alltalkbeta branch on start 2024-11-05 07:57:05 +00:00
erew123 0e61d0aa24 Added F5-TTS engine 2024-11-05 00:15:04 +00:00
erew123 834f7a4454 Added F5-TTS engine 2024-11-05 00:12:44 +00:00
erew123 a8ed41a53b text correction 2024-11-05 00:04:43 +00:00
erew123 2c2c31ef09 F5-TTS final updates 2024-11-05 00:03:47 +00:00
erew123 75a3b68551 Update tts_server.py close warning on line 42 2024-11-04 22:47:02 +00:00
erew123 5d43b23eb7 F5-TTS Engine/Settings changes 2024-11-04 22:27:19 +00:00
erew123 bcd84a4c20 Setting for float16 
# Set Parler Precision. Options are:
        #     "float32" (full precision)
        #     "float16" (half precision)
        #     "bfloat16" (brain floating point)
 2024-11-03 20:24:24 +00:00
erew123 a56a2bae5c f5tts - still a work in progress 
Just uploading this so I have a reference point in time that I wont lose.
 2024-11-03 15:11:50 +00:00
erew123 82f4c29c7d f5tts requirements file 2024-11-03 13:12:16 +00:00
erew123 8e466ee119 Update tts_server.py 2024-11-03 12:57:43 +00:00
erew123 6ba6549f0f Audio Sample Text reference for F5-TTS engine 2024-11-03 11:39:50 +00:00
erew123 630cc61057 Update README.md 2024-10-31 17:09:43 +00:00
erew123 99f36bd4fa Merge pull request #383 from Paladinium/alltalk_beta_rvc_cache 
Introduce LRU cache for RVC
 2024-10-31 16:57:26 +00:00
erew123 d7ac6c401a Merge pull request #393 from UXVirtual/rvc-tts-server-fix 
Fix for missing pitch when calling run_rvc OpenAI endpoint
 2024-10-31 15:52:44 +00:00
erew123 ac884fa10c Update requirements_textgen.txt 2024-10-31 09:14:18 +00:00
erew123 afc9543f6d Update requirements_colab.txt 2024-10-31 09:14:00 +00:00
erew123 f4ac29699a Update requirements_standalone.txt 2024-10-31 09:13:41 +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 75db4f6340 Dropped back Faiss. Should be fixed 2024-10-22 23:01:03 +01:00
erew123 dc2b5dc2fb Locked pytorch::faiss-cpu=1.9.0=py3.11_h491596c_0_cpu 
Because Facebook messed up the installer on the next release, so locked to version pytorch::faiss-cpu=1.9.0=py3.11_h491596c_0_cpu for now
 2024-10-22 22:10:12 +01:00