{"id":12035,"date":"2020-05-10T08:27:32","date_gmt":"2020-05-10T15:27:32","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=12035"},"modified":"2020-05-10T15:48:59","modified_gmt":"2020-05-10T22:48:59","slug":"bringing-back-horrible-sax-solos-with-google-ai","status":"publish","type":"post","link":"http:\/\/jnack.com\/blog\/2020\/05\/10\/bringing-back-horrible-sax-solos-with-google-ai\/","title":{"rendered":"Bringing back horrible sax solos with Google AI"},"content":{"rendered":"\n<p>&#8220;<a href=\"https:\/\/getyarn.io\/yarn-clip\/704ab0e3-d3d2-4351-af4d-e680314e01d6\">Dynamite saxophone solos in rock n&#8217; roll songs<\/a>&#8221; kinda died, <a href=\"http:\/\/www.30rockquotes.net\/seasons\/Season_5\/30rockquotes_plan_b.cfm?quote=12938\">per 30 Rock<\/a>, back in the 80&#8217;s, but thanks to my colleagues in machine learning (who are truly doing God&#8217;s work &#x1f643;), perhaps they&#8217;ll soon be back:<\/p>\n\n\n\n<figure class=\"wp-block-embed-twitter wp-block-embed is-type-rich is-provider-twitter\"><div class=\"wp-block-embed__wrapper\">\nhttps:\/\/twitter.com\/HanoiHantrakul\/status\/1258803013948342272?s=20\n<\/div><\/figure>\n\n\n\n<p>I&#8217;m told that the model requires ~10-15 minutes of audio training data, and once it&#8217;s ready you can apply a transfer in around 2-3 seconds.<\/p>\n\n\n\n<p>Perhaps now we&#8217;ll all be Jack Blacks (Jacks Black?) &#x1f3b7;<\/p>\n\n\n\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"Tenacious D -  Sax a Boom\" width=\"604\" height=\"340\" src=\"https:\/\/www.youtube.com\/embed\/KenyufNno5c?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n\n\n\n<p>[Via Sehmon Burnam]<\/p>\n","protected":false},"excerpt":{"rendered":"<p>&#8220;Dynamite saxophone solos in rock n&#8217; roll songs&#8221; kinda died, per 30 Rock, back in the 80&#8217;s, but thanks to my colleagues in machine learning (who are truly doing God&#8217;s work &#x1f643;), perhaps they&#8217;ll soon be back: I&#8217;m told that the model requires ~10-15 minutes of audio training data, and once it&#8217;s ready you can [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[8],"tags":[],"_links":{"self":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/12035"}],"collection":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/comments?post=12035"}],"version-history":[{"count":3,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/12035\/revisions"}],"predecessor-version":[{"id":12039,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/12035\/revisions\/12039"}],"wp:attachment":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=12035"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=12035"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=12035"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}