bark
bark copied to clipboard
🔊 Text-Prompted Generative Audio Model
Hi everyone, This is not necessarly an issue but I wanted to share my experience with bark and maybe get additionnal information about how it works to maybe mitigate issues...
torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 20.00 MiB (GPU 0; 5.80 GiB total capacity; 5.64 GiB already allocated; 15.69 MiB free; 5.65 GiB reserved in total by PyTorch)...
As all English ascents are american, any chance of any british ascents as the model would become more useful that way.
I discovered Bark today, been trying to simple generate the test sample from the README, but Bark hangs my resources until I interrupt the process. All packages are installed without...
Hi guys! Great work, the quality is really next level. Did you maybe publish a paper or a blog how your method works? Or is code the ground truth here?...
For example, there are multiple gpus on my machine, which requires how to set it up to run the program on multiple gpu at the same time
For example, the MP3 of the collected sound, or the sound in `https://elevenlabs.io/voice-lab`.
Hey there, I was wondering if there is a way to make the speech slower, more clear. Currently it feels too fast and hard to listen. Here's the code I...
hi, i found that bark use hybrid vocab but audiolm use cross attention to inject information in transformer. I wonder the difference between these two methods. And is there any...
I want cite your work in my research paper, do you have any published manuscript or paper link? Or I just cite your work with this code repo? Nice work...