FastSpeech2 is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
These projects were analysed and named FastSpeech2 among their alternatives. The relationship is not symmetric — how FastSpeech2 rates them is a separate judgement, made when FastSpeech2 is analysed in its own right.
calls FastSpeech2 “Clean minimal FastSpeech2 reference, but unmaintained for ~3 years and without a multi-speaker Chinese training recipe.”
Chinese Mandarin tts text-to-speech 中文 (普通话) 语音 合成 , by fastspeech 2 , implemented in pytorch, using waveglow as vocoder, with biaobei and aishell3 datasets