yangdongchao / Text-to-sound-Synthesis

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

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

yangdongchao/Text-to-sound-Synthesis Issues

how to control the duration of the generated audio
Updated 5 months ago
ModuleNotFoundError: No module named 'clip'
Updated 8 months ago
Missing required files for audiocaption evaluation
Updated a year ago3
Pre-trained model on audiocaps
Updated a year ago
Where is the pretrained model for vocoder?
Updated a year ago1
Please add a LICENSE file
Updated a year ago
Unable to access the pre-trained models
Updated a year ago
Add License
Updated a year ago
Location of audiocaps database
Closed a year ago
Pre-trained model Download issue
Updated a year ago1
Pretrained model
Closed a year ago1
provide examples with [mask] token?
Updated a year ago2
Can Diffsound do unconditional generation?
Closed a year ago
在线期待一个像disco diffusion的colab版本
Updated 2 years ago2
Embedding shape issue
Updated 2 years ago4
ModuleNotFoundError: No module named 'vocoder'
Closed 2 years ago1
Storage of models and more
Updated 2 years ago2
Where to download the melception.pt to evaluate?
Updated 2 years ago2
About CC_pretrained model
Closed 2 years ago1
How do we use BERT or CLIP features?
Closed 2 years ago1
Issues from sampling by newest pretrained model
Closed 2 years ago2
How to use the codebook with the size of 512?
Closed 2 years ago3
Baidu link
Updated 2 years ago2
Missing libraries "ftfy" "regex" "einops"
Updated 2 years ago3
KeyError: 'visual.layer1.0.conv1.weight'
Closed 2 years ago3
ImportError: cannot import name 'rank_zero_warn' from 'pytorch_lightning.utilities.distributed'
Closed 2 years ago3
Missing package "image_synthesis"
Closed 2 years ago4