bark icon indicating copy to clipboard operation
bark copied to clipboard

🔊 Text-Prompted Generative Audio Model

Results 307 bark issues
Sort by recently updated
recently updated
newest added

Is it possible to get deterministic results so the same input prompt always gives the same audio? I don't see any way to set the seed.

I followed the install instructions. When I try starting with START_BARK_INFINITY.bat, this is the error I get. ----------------------------------------------------------------------------------- Running command: "C:\Bark_Infinity\installer_files\conda\condabin\conda.bat" activate "C:\Bark_Infinity\installer_files\env" >nul && conda Running command: "C:\Bark_Infinity\installer_files\conda\condabin\conda.bat" activate...

max number of tokens I am able to run thru bark generate_text_semantic() is about 40, ~ 24 words or so. I looked thru the code and noticed that generate_text_semantic() clips...

The Chirp link in the README.md file links to https://suno.ai/examples/chirp-v1 which returns a 404. you may want to update it.

Removed early access form that sent people to Typeform

I've searched a lot for information about this, I expected to find guides or users sharing tips, or some official documentation, but found only the minimal stuff in the docs:...

The link was wrong, there's 404 at https://www.suno.ai/examples/bark-v0. Also note that there's 404 at https://www.suno.ai/examples/chirp-v1, and there's no such page publicly available on https://suno-ai.notion.site/Suno-Examples-de4aa9eddc6d4a22a23d45ee286223e9. Probably you just forgot to share...

I'm working with IPA for the Mohegan-Pequot language and do not see any options to indicate to the model that I am inputting IPA directly. Example IPA: nʌhkˈʌnˈɔ̃ŋk nʌtˈɔ̃hkwamˈam‖ Mohegan:...

Partially solve OUT OF MEMORY problem by preload modules on demand versus preload all modules at the same time. After these modifies, run smoothly on my 8GB graphic card.

This is more a broad question about the model/project instead of a real issue. Is it possible with the actual project to timestamp the generated audio, word by word? Something...