Mozer / talk-llama-fast

Port of OpenAI's Whisper model in C/C++ with xtts and wav2lip
MIT License
742 stars 68 forks source link

incomplete video tutorial and errors #35

Open cerulliber opened 1 month ago

cerulliber commented 1 month ago

greetings,

1.I don't understand how to set environment variables. this isn't in written description, only in youtube video. exact time, up to 9:33: https://youtu.be/0MEZ84uH4-E?t=542 unfortunately, your windows is in russian and it's 11 no 10 so may be differences do I need to go to system properties>Advanced>Environment variables>new> add path to C:\talk-llama-fast-0.2.0\xtts\SillyTavern-Extras\tts_out ?

2.you also skipped h264 codec. currently availabe, don't know which one to get: http://ciscobinary.openh264.org/openh264-2.4.1-win32.dll.bz2 http://ciscobinary.openh264.org/openh264-2.4.1-win32.dll.signed.md5.txt http://ciscobinary.openh264.org/openh264-2.4.1-win64.dll.bz2 http://ciscobinary.openh264.org/openh264-2.4.1-win64.dll.signed.md5.txt

  1. where do I put models ggml-medium.en-q5_0 and mistral-7b-instruct-v0.2.Q5_0 ? straight into \talk-llama-fast-0.2.0 folder?
  2. when running xtts_wav2lip.ba got this error C:\Users\xxx\miniconda3\envs\xtts\Lib\site-packages\pydantic_internal_fields.py:161: UserWarning: Field "modelname" has conflict with protected namespace "model".

I can't thank you enough for your work!

cerulliber commented 1 month ago

WARNING: model is not multilingualrun: processing, 4 threads, lang = en, task = transcribe, timestamps = 0 ...

cerulliber commented 3 weeks ago

pls help. thanks!

Fuckingnameless commented 2 weeks ago

if you can't create a simple python venv what are you doing here?

Wuzzooy commented 2 weeks ago

1) if you read the tutorial it points to this link with a tutorial on how to install ffmpeg and set env variable https://phoenixnap.com/kb/ffmpeg-windows. It's just a path that will point to where you installed ffmpeg so it depends of where you install it so don't copy paste other people path. for example you install it directly in C:\ the path will look like this C:\ffmpeg\bin like shown in the link but you are not forced to install it there if you don't want to.

2)If your windows is 64 bit which i guess it it, use win64.

3)put the model where you start script .bat

4)i've seen this warning which is a warning not an error but it will still work without issue so you can ignore it

I know that chatgpt can hallucinate but it can greatly help with stuff like this, yes AI can do more than "RP"

cerulliber commented 1 week ago

(xtts) C:\t\xtts>pip install git+https://github.com/Mozer/tts error: subprocess-exited-with-error

× Building wheel for TTS (pyproject.toml) did not run successfully. │ exit code: 1 ╰─> [2640 lines of output]

error: Microsoft Visual C++ 14.0 or greater is required. Get it with "Microsoft C++ Build Tools": https://visualstudio.microsoft.com/visual-cpp-build-tools/ [end of output]

pip install -r requirements.txt note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for TTS Failed to build TTS ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (TTS)

  error: Microsoft Visual C++ 14.0 or greater is required. Get it with "Microsoft C++ Build Tools": https://visualstudio.microsoft.com/visual-cpp-build-tools/
  [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for TTS Failed to build TTS ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (TTS) error: Microsoft Visual C++ 14.0 or greater is required. Get it with "Microsoft C++ Build Tools": https://visualstudio.microsoft.com/visual-cpp-build-tools/ [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for TTS Failed to build TTS ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (TTS)


I installed this not sure it's working https://visualstudio.microsoft.com/visual-cpp-build-tools/ too bad tutorial it's incomplete and need at least git (not listed) and visual studio (not listed, don't know what to install)

any help will be highly appreciated. I really want this installed. thanks!

Wuzzooy commented 1 week ago

Yeah this error is self explanatory, to build the tts wheel(coqui xtts) you need visual studio tools and yeah the link provided is the right one. You can check visual studio installation by typing cl in the terminal window You should see something like this after pressing enter if it's correctly installe

Microsoft (R) C/C++ Optimizing Compiler Version 19.40.33812 for x64
Copyright (C) Microsoft Corporation.  All rights reserved.

usage: cl [ option... ] filename... [ /link linkoption... ]

If you still have issue with visual studio, follow this tutorial, since the tutorial is a bit old, the version of your visual studio will be different but it doesn't matter. https://github.com/bycloudai/InstallVSBuildToolsWindows

edit:

It was actually in the tutorial

I remember that when I first installed xtts-api-server it asked to install some full version of [visual-cpp-build-tools](https://visualstudio.microsoft.com/ru/visual-cpp-build-tools/). The default download page from MS wasn't working for me, so i had to google and found it elsewher. [VS_BuildTools.exe screenshot 1](https://github.com/Mozer/talk-llama-fast/assets/1599013/23627998-28f7-4eeb-9bc5-be54c1a68217), [screenshot 2](https://github.com/Mozer/talk-llama-fast/assets/1599013/b7ff8401-c5b3-4f5c-abdb-e527f296b12d). Or maybe it was [VC_redist.x86.exe](https://learn.microsoft.com/ru-ru/cpp/windows/latest-supported-vc-redist?view=msvc-170).