FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis
Open paper
Benchmark
Model
Rank
Results
text-to-speech-synthesis-on-ljspeech
FastDiff (4 steps)
#7
Audio Quality MOS: 4.28
text-to-speech-synthesis-on-ljspeech
FastDiff-TTS
#8
Audio Quality MOS: 4.03
Rank counts only results with a code link.