FastSpeech: Fast, Robust and Controllable Text to Speech
Open paper
Benchmark
Model
Rank
Results
text-to-speech-synthesis-on-ljspeech
FastSpeech (Mel + WaveGlow)
#10
Audio Quality MOS: 3.84
text-to-speech-synthesis-on-ljspeech
Merlin
#12
Audio Quality MOS: 2.4
Rank counts only results with a code link.