Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
Open paper
Benchmark
Model
Rank
Results
speech-synthesis-on-libritts
Vocos
#10
PESQ: 3.70
Periodicity: 0.101
V/UV F1: 0.9582
Rank counts only results with a code link.