Getting RVC to work

[Airmiz]

When I generate it runs and completes, but no sentences or audio is output.

Steps on how to get RVC working?
thanks,

[lukaszliniewicz]

Does it generate audio without RVC? To get RVC, you need to install RVC_CLI (https://github.com/blaise-tk/RVC_CLI). There are instructions in its repository.

[Airmiz]

right, I have the pth and index, it just crashes every time I attempt.

[lukaszliniewicz]

Sorry, just to confirm: you have installed RVC_CLI and it is running? Does it crash without RVC? How have you installed Pandrator, with the installer?

[Airmiz]

Correct, Pandrator base running and work. What do you mean by RVC_CLI running?

[lukaszliniewicz]

Just if you can start it and if it's running alongside Pandrator.

[lukaszliniewicz]

From their documentation:

Windows
Execute the [install.bat](https://github.com/blaise-tk/RVC_CLI/blob/main/install.bat) file to activate a Conda environment. Afterward, launch the application using env/python.exe main.py instead of the conventional python main.py command.

If you cloned the repository into, say, C:/AI, then run the install.bat from there, you would open Windows Terminal in that folder (right click and select the option to open the terminal) and run env/python.exe main.py.

[lukaszliniewicz]

Sorry, the actual command is env/python.exe main.py api.

[Airmiz]

This what I get running the generation with the API open

INFO: Started server process [12960]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)
INFO: 127.0.0.1:52083 - "POST /infer HTTP/1.1" 500 Internal Server Error
ERROR: Exception in ASGI application

[cif232]

I ran into (what I think is the same issue) but was able to resolve it by making the change in this comment:
blaisewf/RVC_CLI#31 (comment)

to the api.py file from RVC_CLI .

Specifically changing the infer api to

@app.post("/infer")
async def infer(request: Request):
    command = ["python", "main.py", "infer"]

    json_data = await request.json()

    command += [f"--{key}={value}" for key, value in json_data.items()]

    return execute_command(command)

[Airmiz]

That fix the API error, now it just isn't generating any sentences/wav files.

[Airmiz]

using VoiceCraft if that is any help