Can this model be included in the diffusers pipeline?
Nice work for audio generation! Recently I have been looking for end-to-end audio waveform generation diffusion models, Stable Audio works well, but it costs too much GPU memory. If you have time, could you integrate this work into diffusers? That way, I can easily integrate it into my work.
By the way, the code in this model card is different from that on GitHub.
By the way, the code in this model card is different from that on GitHub.
We wish to integrate our model into the diffusers but might need assistance from individuals with experience in integrating models into diffusers, hopefully we will submit pr in late December.
Currently, the model is user-friendly and can be run with just a few lines of code via our GitHub repository: https://github.com/haidog-yaqub/EzAudio