tianjiao du
tianjiao du
the num of paras in text condition model is only 562M rather than 857M in mousai paper, is there any extra config in text condition model?
Is there any open-source well-trained ckpt to be used for ControlNet?
> Comment out this line of code ：/mnt/bn/lqhaoheliu/exps/checkpoints/audioldm/2023_04_07_audioldm_clap_v2_yusong/music_speech_audioset_epoch_15_esc_89.98.pt
> Can you try the folllowing: > > ```python > import torch > import torchaudio > from tango import Tango > from tools.torch_tools import wav_to_fbank > > filename = ......
> What is the exact issue when reconstructing a 3.7s audio? Does it generate noise for the entire 3.7s or the last 0.1s? When the VAE reconsturct a 3.7s audio,...
Hi, I encountered a similar issue. When training BPE with ETH data, the RAM usage is around 20GB, and the training completes in just a few minutes. However, with Unigram,...
I have the same question
> Hi, I found that the `can_bus` in the info is an array of length 18. There is only a brief description in the repo (position, speed, acceleration, steering, lights,...