FastSpeech 2: Fast and High-Quality End-to-End Text to Speech · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2006.04558/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTFastSpeech 2: Fast and High-Quality End-to-End Text to Speech — mentioned by nmfisherhttps://news.ycombinator.com/item?id=34271860urn:hackerpapers:mention:2006.04558:34271860Fri, 06 Jan 2023 07:16:05 GMT<p>My app [0] currently uses a mildly customized version of FastSpeech 2 [1] with LPCNet [2] vocoder, which I consider &quot;good quality&quot; @ 16kHz. Faster than realtime on mobile CPU (at least, on anything upwards of a mid-range 2017 device - I can stream practically instantly on my iPhone 11). Using a different vocoder with mobile GPU could probably get even faster (which I don&#x27;t want to do, for various reasons), and desktop CPU is usually even faster. There are various other flavours that can deliver faster synthesis (NixTTS comes to mind), but IMO they sacrifice quality even further. &quot;Good…</p><p><a href="https://hackerpaper.kaipfister.de/p/2006.04558/">Paper and discussion history</a>. A mention is not an endorsement.</p>eess.AS