WaveRNN 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 WaveRNN among their alternatives. The relationship is not symmetric — how WaveRNN rates them is a separate judgement, made when WaveRNN is analysed in its own right.
calls WaveRNN “choose for a lightweight WaveRNN-based TTS/vocoder rather than a multi-model toolkit.”
:robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
calls WaveRNN “Autoregressive WaveRNN TTS+vocoder, slower and English-only; a swap only for a small readable legacy pipeline.”
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