https://hackerpaper.kaipfister.de/p/2112.02418/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=29787417urn:hackerpapers:mention:2112.02418:29787417Mon, 03 Jan 2022 21:47:11 GMT<p>Demo: https://coqui.ai Code: https://github.com/coqui-ai/tts Blogpost: https://coqui.ai/blog/tts/yourtts-zero-shot-text-synthesis-l... Paper: https://arxiv.org/abs/2112.02418</p><p><a href="https://hackerpaper.kaipfister.de/p/2112.02418/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.SDhttps://news.ycombinator.com/item?id=29787101urn:hackerpapers:mention:2112.02418:29787101Mon, 03 Jan 2022 21:21:34 GMT<p>The Brazilian Portuguese model is a bit of an extreme showcase (and thus really cool!), as it was trained on a single speaker (entirely recorded by the main author of the paper, Edresson Casanova, who&#x27;s Brazilian). The fact that it can do multi-lingual voice cloning at all in that case is already surprising. You can find more details in the project page [0] and paper [1]. And here&#x27;s the corpus. [2] [0] https://edresson.github.io/YourTTS/ [1] https://arxiv.org/abs/2112.02418 [2] https://edresson.github.io/TTS-Portuguese-Corpus/</p><p><a href="https://hackerpaper.kaipfister.de/p/2112.02418/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.SD