Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
My CPU is amd 3900x, but it cost 5s to tts of the '今天的天气真不错啊',
and cost 3s convert the zh.wav to '我认为跑步最重要的就是给我带来了身体健康',
it is too slow for use for even for a single device.