bytedance/Make-An-Audio-2
a text-conditional diffusion probabilistic model capable of generating high fidelity audio.
PythonMIT
Issues
- 3
Reproduce results
#3 opened by MoayedHajiAli - 0
can't find configs/research
#7 opened by kily-wmz - 0
the evaluation of variable length generation
#6 opened by dalision - 1
- 1
VAE's training data
#5 opened by hkchengrex - 1
stereo and higher sampling rates
#2 opened by wlf0322