{"id":38386,"date":"2023-02-06T16:50:04","date_gmt":"2023-02-06T21:50:04","guid":{"rendered":"https:\/\/mjtsai.com\/blog\/?p=38386"},"modified":"2023-02-14T15:20:01","modified_gmt":"2023-02-14T20:20:01","slug":"podsearch-reborn","status":"publish","type":"post","link":"https:\/\/mjtsai.com\/blog\/2023\/02\/06\/podsearch-reborn\/","title":{"rendered":"PodSearch Reborn"},"content":{"rendered":"<p><a href=\"https:\/\/www.david-smith.org\/blog\/2023\/02\/02\/podsearch-reborn\/\">David Smith<\/a>:<\/p>\n<blockquote cite=\"https:\/\/www.david-smith.org\/blog\/2023\/02\/02\/podsearch-reborn\/\">\n<p><a href=\"https:\/\/david-smith.org\/blog\/2017\/01\/12\/podsearch-a-random-side-project\/\">Back in 2017<\/a> I had created a <a href=\"https:\/\/podsearch.david-smith.org\">site<\/a> which took the the audio of some of my favorite podcasts and tried to make them searchable by passing them through an automated speech-to-text engine.<\/p>\n<p>[&#8230;]<\/p>\n<p>Thankfully since then OpenAI has released <a href=\"https:\/\/github.com\/openai\/whisper\">Whisper<\/a> a powerful speech-to-text engine that I can run right on my Mac and results in transcripts that are shockingly good.  They aren&rsquo;t quite at the level of a human transcriber but they get darn close in many instances.  Getting close to the level where you could use them to grab a pull quote with only a little bit of tidying up to do.<\/p>\n<\/blockquote>\n\n<p>Previously:<\/p>\n<ul>\n<li><a href=\"https:\/\/mjtsai.com\/blog\/2017\/01\/13\/podsearch\/\">PodSearch<\/a><\/li>\n<\/ul>\n\n<p id=\"podsearch-reborn-update-2023-02-14\">Update (2023-02-14): <a href=\"https:\/\/sixcolors.com\/post\/2023\/02\/automating-podcast-transcripts-on-my-mac-with-openai-whisper\/\">Jason Snell<\/a>:<\/p>\n<blockquote cite=\"https:\/\/sixcolors.com\/post\/2023\/02\/automating-podcast-transcripts-on-my-mac-with-openai-whisper\/\">\n<p>While not perfect, Whisper was <em>staggeringly<\/em> better than the 2017 transcript and really, much better than any other AI-driven transcription I&rsquo;d tried recently. It got the punctuation. It got proper names. And it didn&rsquo;t turn &ldquo;Thanks for listening to The Incomparable, I&rsquo;ve been your host Jason Snell&rdquo; into &ldquo;Goodnight everybody for listening to be uncomfortable, I&rsquo;ve been your Hostess and smell.&rdquo;<\/p>\n<p>Fortunately, a fellow named Georgi Gerganov made a <a href=\"https:\/\/github.com\/ggerganov\/whisper.cpp\">C++-native port of Whisper<\/a> that is easy to install and run on macOS and is optimized for Apple silicon. I downloaded and installed Gerganov&rsquo;s version, downloaded the medium English model, and discovered that it could transcribe a podcast at rates up to 2x!<\/p>\n<p>This was great, but the last thing I needed was to have to remember all the arcane command-line commands required to get the files in the right place. So instead, I wrote <a href=\"https:\/\/www.icloud.com\/shortcuts\/10daa20be4774b629a04e214416ed3e2\">The Transcriptor<\/a>, a Shortcut that lets me control-click on audio files and turn them into transcripts in a format of my choice.<\/p>\n<\/blockquote>","protected":false},"excerpt":{"rendered":"<p>David Smith: Back in 2017 I had created a site which took the the audio of some of my favorite podcasts and tried to make them searchable by passing them through an automated speech-to-text engine. [&#8230;] Thankfully since then OpenAI has released Whisper a powerful speech-to-text engine that I can run right on my Mac [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"apple_news_api_created_at":"2023-02-06T21:50:08Z","apple_news_api_id":"eda3ea41-5cc1-4433-a083-2f9807b7b676","apple_news_api_modified_at":"2023-02-14T20:20:05Z","apple_news_api_revision":"AAAAAAAAAAAAAAAAAAAAAQ==","apple_news_api_share_url":"https:\/\/apple.news\/A7aPqQVzBRDOggy-YB7e2dg","apple_news_coverimage":0,"apple_news_coverimage_caption":"","apple_news_is_hidden":false,"apple_news_is_paid":false,"apple_news_is_preview":false,"apple_news_is_sponsored":false,"apple_news_maturity_rating":"","apple_news_metadata":"\"\"","apple_news_pullquote":"","apple_news_pullquote_position":"","apple_news_slug":"","apple_news_sections":"\"\"","apple_news_suppress_video_url":false,"apple_news_use_image_component":false,"footnotes":""},"categories":[2],"tags":[74,112,343,787,96],"class_list":["post-38386","post","type-post","status-publish","format-standard","hentry","category-technology","tag-opensource","tag-podcasts","tag-search","tag-speech-recognition","tag-web"],"apple_news_notices":[],"_links":{"self":[{"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/posts\/38386","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/comments?post=38386"}],"version-history":[{"count":2,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/posts\/38386\/revisions"}],"predecessor-version":[{"id":38456,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/posts\/38386\/revisions\/38456"}],"wp:attachment":[{"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/media?parent=38386"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/categories?post=38386"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/tags?post=38386"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}