bark
bark copied to clipboard
suno-ai
🔊 Text-Prompted Generative Audio Model
Hi ! Could you explain is there oportunity to change models storage folder ? I have small system disk with no free space. All models are downloading to Users/.cashe folder...
what other mannerisms are supported? i know at least [laughs], and [sighs] works but what other words are supported in brackets invoke different sounds?
Hi there again ! I have low free space in system disk,, so the question is - is there any oportunities to add local CUDA support without install ? Possible...
Is the only way to choose gender to do MEN: Phrase WOMEN: Phrase Or are there any alternative ways?
I'm trying to run by1070 8Gb, but have only this: CUDA out of memory. Tried to allocate 16.00 MiB (GPU 0; 8.00 GiB total capacity; 7.33 GiB already allocated; 0...
Can you speak a bit more on the training of the dataset. Which datasets did you use? How long did you train? etc. Hugging face made this interactive tool that...
Hi, was not able to use the following code to generate the audio: ``` from bark import SAMPLE_RATE, generate_audio, preload_models from IPython.display import Audio # download and load all models...
Hello, I am not able to run Bark locally because it gets stuck at the "preload_models()" step. Here is the error it gives me, I have upgraded my huggingface but...
It seems there are limits word Bark can read in each time, I am wondering it is possible for Bark to read long text?
