kromskii2/alltalk_tts
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
984 Commits 2 Branches 23 Tags
90af3c2ec52a4474daea64932b81ef397e2ecdb0
Commit Graph
984 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
erew123 f15dcd23a7 Fix Coqui TTS to 0.24.3 
resolved bug in current 0.25.0 version
 2024-12-08 03:02:02 +00:00
ekirts-h e155d8eb22 Fix to disable BPE and VAD 
Swap the string "True" / "False" to boolean before passing as they always return True in if statement and does not properly disable the functions even when set to disable in webui.
 2024-12-07 20:19:09 +13:00
ekoc 46a023829d Use pydantic for config serialization/deserialization 2024-12-04 21:57:12 +01:00
erew123 239b656633 Merge pull request #427 from hykilpikonna/alltalkbeta 
[F] Fix #251: Expected a value of type 'str'
 2024-11-29 04:41:38 +00:00
Azalea Gui 0c6e113aff [F] Fix #251: Expected a value of type 'str' 2024-11-28 22:19:44 -05:00
erew123 94f90e149e Update python-ci.yml 2024-11-27 19:43:26 +00:00
erew123 cc160820c4 Update README.md 2024-11-27 19:37:23 +00:00
erew123 af29b1ed75 Added "hi" hindi language 
I believe the tokenizers now support Hindi, but don't know for sure. Will require the XTTS 2.0.3 model. Anything earlier doesn't support Hindi.
 2024-11-27 05:11:01 +00:00
erew123 1297a28cb4 Export to MP3 option 2024-11-27 05:00:56 +00:00
erew123 415b9357b0 Update python-ci.yml 2024-11-27 03:55:19 +00:00
erew123 f46796d121 Update python-ci.yml 2024-11-27 03:38:16 +00:00
erew123 fae005f59d Delete .github/workflows/publish-docker.yml 2024-11-27 03:36:08 +00:00
erew123 66d5090b2e Update README.md 2024-11-27 03:19:41 +00:00
erew123 65ba0d73ac python-ci.yml alltalkbeta only 
on:
  push:
    branches:
      - alltalkbeta
  pull_request:
    branches:
      - alltalkbeta
 2024-11-27 03:04:53 +00:00
erew123 0b232bdb7c Added SSL Proxy 2024-11-27 02:08:21 +00:00
erew123 b51e9cde2f SSL Proxy 2024-11-27 02:07:15 +00:00
erew123 1bed9f586e UPD Help content 2024-11-27 02:06:24 +00:00
erew123 e220d70e7e PyOpenSSL 2024-11-27 02:05:06 +00:00
erew123 1be14414cf Add files via upload 2024-11-26 22:03:57 +00:00
erew123 2819e09063 Add files via upload 2024-11-26 22:00:30 +00:00
erew123 f92ea060b0 Update basediagnostics.log 2024-11-26 03:00:45 +00:00
erew123 72a495c108 basediagnostics.log updated 2024-11-26 03:00:03 +00:00
erew123 abd4eb8450 lint cleanup 2024-11-26 02:27:27 +00:00
erew123 9309303ccb Updated TGWUI Remote Extension 2024-11-26 00:48:45 +00:00
erew123 393bff6ab9 Update atsetup.sh 2024-11-26 00:23:42 +00:00
erew123 7c23b043d9 Update atsetup.bat 2024-11-26 00:20:18 +00:00
erew123 c44f17cd38 Update atsetup.sh ffmpeg 2024-11-25 23:37:21 +00:00
erew123 3ed501badc Update atsetup.bat FFmpeg 2024-11-25 23:35:53 +00:00
erew123 231bc21fa7 Updated to use new ffmpeg 2024-11-25 23:33:12 +00:00
erew123 aa794e458b Updated Transcode functions 
new FFmpeg install required:
ffmpeg-python>=0.2.0
conda install -c conda-forge ffmpeg=*=*gpl*
 2024-11-25 23:32:07 +00:00
erew123 72af6c2455 changed to ffmpeg-python>=0.2.0 2024-11-25 23:30:57 +00:00
erew123 a941cffcc0 Command-Line Arguments 
7. **Command-Line Arguments**:
    - Accepts a `--tts_model` argument to bypass the interactive menu and directly set up a specific TTS engine
      on the first time start-up:
        - `piper`: Sets up the Piper TTS engine.
        - `vits`: Sets up the VITS TTS engine.
        - `xtts`: Sets up the XTTS TTS engine.
        - `none`: Skips model setup entirely.
 2024-11-25 22:01:51 +00:00
erew123 19359f542b cmdline arguments for first run 
**Command-Line Arguments**:
    - Accepts a `--tts_model` argument to bypass the interactive menu and directly set up a specific TTS engine
      on the first time start-up:
        - `piper`: Sets up the Piper TTS engine.
        - `vits`: Sets up the VITS TTS engine.
        - `xtts`: Sets up the XTTS TTS engine.
        - `none`: Skips model setup entirely.
 2024-11-25 22:01:17 +00:00
erew123 9d319ecb3a added extra transcoding logging for debug 2024-11-25 16:30:52 +00:00
erew123 f16f6b9498 Correct passing latent:voice on narrator 2024-11-25 05:25:21 +00:00
erew123 856d67fe5b Updated firstrun better docker/colab support 
In Docker or Google colab environments where people may not have access to a keyboard, just download piper (as its small) and dont wait the 60 seconds for a keypress.
 2024-11-25 01:35:04 +00:00
erew123 50cafba12f Google colab detection fix 2024-11-25 00:33:37 +00:00
erew123 3d3047fb93 Update tts_server.py 2024-11-24 23:53:13 +00:00
erew123 883d8a82d0 Update script.py 2024-11-24 23:51:11 +00:00
erew123 a23dcf6de7 current_commit_sha correction 2024-11-24 23:36:56 +00:00
erew123 bb55313b9e Update README.md 2024-11-24 20:24:50 +00:00
erew123 c7cfed60fe Update README.md 2024-11-24 12:02:46 +00:00
erew123 eef198eae1 Merge pull request #417 from erew123/configrework 
AllTalk Version 2 Complete
 2024-11-24 11:59:55 +00:00
erew123 06b28c1ce7 Merge pull request #414 from Paladinium/configrework 
Adding github action for CI
 2024-11-24 11:49:45 +00:00
erew123 1c09bb985a lint 2024-11-24 11:49:21 +00:00
erew123 3cb30504e5 Try statement to capture missing imports 
hopefully will catch those whom don't reinstall requirements
 2024-11-24 11:30:03 +00:00
erew123 c0498ed8c9 Add files via upload 2024-11-24 11:14:00 +00:00
erew123 a5550bb254 script.py & tts_server.py updates 2024-11-24 11:12:15 +00:00
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