FastSpeech 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 FastSpeech among their alternatives. The relationship is not symmetric — how FastSpeech rates them is a separate judgement, made when FastSpeech is analysed in its own right.
calls FastSpeech “First-generation FastSpeech: cheaper to train but lower quality and long unmaintained.”
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