serp-ai / bark-with-voice-clone

🔊 Text-prompted Generative Audio Model - With the ability to clone voices
https://serp.ai/tools/bark-text-to-speech-ai-voice-clone-app
Other
3.05k stars 406 forks source link

preload_models() got an unexpected keyword argument 'path' #31

Open juandavidGF opened 1 year ago

juandavidGF commented 1 year ago

after generate the .npz output file,

I got a error running the cell: `

download and load all models

preload_models( text_use_gpu=True, text_use_small=False, coarse_use_gpu=True, coarse_use_small=False, fine_use_gpu=True, fine_use_small=False, codec_use_gpu=True, force_reload=False, path="models" )`

the error is "TypeError: preload_models() got an unexpected keyword argument 'path'"

I tried to change the default "models" for "path="./output.npz"" but didn't work. what the path should to be?

image
dagshub[bot] commented 1 year ago

Join the discussion on DagsHub!

francislabountyjr commented 1 year ago

Are you on the latest version? Just tried to reproduce and the models are loading fine on my system.

PSY222 commented 1 year ago

I'm using the latest version, but I am facing the same TypeError :( generation.py includes path variable, but I'm not sure it returns 'unexpected keyword argument' error message.

def preload_models(
    text_use_gpu=True,
    text_use_small=False,
    text_model_path=None,
    coarse_use_gpu=True,
    coarse_use_small=False,
    coarse_model_path=None,
    fine_use_gpu=True,
    fine_use_small=False,
    fine_model_path=None,
    codec_use_gpu=True,
    force_reload=False,
    path=None,
):
    """Load all the necessary models for the pipeline."""
    if _grab_best_device() == "cpu" and (
        text_use_gpu or coarse_use_gpu or fine_use_gpu or codec_use_gpu
    ):
        logger.warning("No GPU being used. Careful, inference might be very slow!")
    _ = load_model(
        model_type="text", use_gpu=text_use_gpu, use_small=text_use_small, force_reload=force_reload, path=path if text_model_path is None else text_model_path
    )
    _ = load_model(
        model_type="coarse",
        use_gpu=coarse_use_gpu,
        use_small=coarse_use_small,
        force_reload=force_reload,
        path=path if coarse_model_path is None else coarse_model_path,
    )
    _ = load_model(
        model_type="fine", use_gpu=fine_use_gpu, use_small=fine_use_small, force_reload=force_reload, path=path if fine_model_path is None else fine_model_path
    )
    _ = load_codec_model(use_gpu=codec_use_gpu, force_reload=force_reload)
aknahin commented 11 months ago

I am also facing same type of error. image

blastbeng commented 1 month ago

Same problem here