yangdongchao / Text-to-sound-Synthesis

The source code of our paper "Diffsound: discrete diffusion model for text-to-sound generation"

Home Page:http://dongchaoyang.top/text-to-sound-synthesis-demo/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Missing package "image_synthesis"

dto opened this issue · comments

commented

(specvqgan) dto@thexder:~/src/tss/Diffsound$ python evaluation/generate_samples_batch.py
Traceback (most recent call last):
File "evaluation/generate_samples_batch.py", line 19, in
from image_synthesis.utils.io import load_yaml_config
ModuleNotFoundError: No module named 'image_synthesis'

Does not seem to be installable through anaconda.

Hi, I am sorry for this. I have been re-write this part code. You can refer to latest code.

commented

Ok, thank you! I am having trouble with paths such as /apdcephfs/share_1316500/donchaoyang/code3, should I simply set up a Linux mount point instead of changing the paths? What is the simplest way to enter new text and hear a result using the pretrained model? I'm excited about using this project for experimental musical sounds.

Ok, thank you! I am having trouble with paths such as /apdcephfs/share_1316500/donchaoyang/code3, should I simply set up a Linux mount point instead of changing the paths? What is the simplest way to enter new text and hear a result using the pretrained model? I'm excited about using this project for experimental musical sounds.

Hi, the path /apdcephf/ is my linux path, you must set it as your own path according to your machine.

I will try to update a notebook file on google colab, which may solve the enviroment problem.