NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality

Benchmark Model Rank Results
text-to-speech-synthesis-on-ljspeechNaturalSpeech#1Audio Quality MOS: 4.56
text-to-speech-synthesis-on-ljspeechVITS#2Audio Quality MOS: 4.43
text-to-speech-synthesis-on-ljspeechFastSpeech 2 + HiFiGAN#5Audio Quality MOS: 4.34