Haohe Liu / 刘濠赫
Haohe Liu / 刘濠赫
@Nu70ry Another quick fix is install laion_clap using the most up-to-date code `pip install git+https://github.com/LAION-AI/CLAP.git` I tried this personally and it works. Hope it helps
Hi Helin @WangHelin1997 , Thanks for your interest. The training script will be available after paper acceptance. I appreciate your understanding. Haohe
If you are interested I can release it next week. Previously I didn't consider releasing it because it's a bit hard to run on a common GPU. Anyway, I can...
@chavinlo please checkout the README for the latest update on model checkpoint
Hi, thanks for your suggestions. Will add it later today.
Hi @hoyeongchoi you can find the VAE and HIFi-GAN checkpoints on Zenodo here: https://zenodo.org/record/7884686#.ZFBb6ezMKbh
> Fixed, please refresh notebook and try again. Many thanks for the help! @olaviinha
@ThibaultCastells Sorry for the delay. You can use the checkpoint ([music_speech_epoch_15_esc_89.25.pt](https://huggingface.co/lukewys/laion_clap/blob/main/music_speech_epoch_15_esc_89.25.pt)) in this repo https://github.com/LAION-AI/CLAP, which can work the same as the CLAP checkpoint we used.
Sorry, we currently do not have plans for adding CPU support since the process could be very slow. I would suggest using google collab, which has free GPU.
Sorry we currently do not have plan for uploading the fine-tuned model.