{"id":255,"date":"2024-10-21T11:07:11","date_gmt":"2024-10-21T15:07:11","guid":{"rendered":"https:\/\/carleton.ca\/xlab\/?p=255"},"modified":"2024-10-21T11:08:02","modified_gmt":"2024-10-21T15:08:02","slug":"homebrewed-software-a-handwriting-transcription-app","status":"publish","type":"post","link":"https:\/\/carleton.ca\/xlab\/2024\/homebrewed-software-a-handwriting-transcription-app\/","title":{"rendered":"Homebrewed Software: A Handwriting Transcription App"},"content":{"rendered":"<p><em>By Shawn Graham<\/em><\/p>\n<p>Continuing from <a href=\"https:\/\/carleton.ca\/xlab\/2024\/transcribing-handwriting-with-a-multimodal-model\/\">the last experiment <\/a>and ruminating on <a href=\"https:\/\/www.dbreunig.com\/2024\/10\/18\/the-3-ai-use-cases-gods-interns-and-cogs.html\">Drew Breunig&#8217;s taxonomy of use cases for AI<\/a> (in short: gods, interns, cogs, and toys) as well as &#8216;<a href=\"https:\/\/electricarchaeology.ca\/2024\/09\/27\/home-cooked-software-for-the-archaeologist-or-historian\/\">homecooked software<\/a>&#8216; I undertook to use Anthrophic&#8217;s &#8216;Claude&#8217; model to see what I could do. I&#8217;m building a cog via Claude&#8217;s &#8216;artifacts&#8217; feature which allows you to iterate on small code snippets, html, etc &#8211; <a href=\"https:\/\/simonwillison.net\/2024\/Oct\/21\/claude-artifacts\/\">Simon Willison does this a lot<\/a> so blame him.<\/p>\n<p>Anyway, the result is a web-app that I called &#8216;handwriter&#8217; &#8211; which is a terrible name &#8211; but permits someone to pass images and multi-page pdfs through the Gemini vision model and get transcribed text back. It handles the prompting and image manipulation.<\/p>\n<p>You can find it at <a href=\"https:\/\/github.com\/shawngraham\/handwriter\">https:\/\/github.com\/shawngraham\/handwriter <\/a><\/p>\n<p><\/p>\n<div id=\"attachment_257\" class=\"wp-caption aligncenter\" style=\"width: 400px\"><img decoding=\"async\" loading=\"lazy\" class=\"size-large wp-image-257\" src=\"https:\/\/carleton.ca\/xlab\/wp-content\/uploads\/en-or-transcribing-handwritten-text-with-python-and-azure-07-400x337.png\" alt=\"\" width=\"400\" height=\"337\" srcset=\"https:\/\/carleton.ca\/xlab\/wp-content\/uploads\/en-or-transcribing-handwritten-text-with-python-and-azure-07-400x337.png 400w, https:\/\/carleton.ca\/xlab\/wp-content\/uploads\/en-or-transcribing-handwritten-text-with-python-and-azure-07-240x202.png 240w, https:\/\/carleton.ca\/xlab\/wp-content\/uploads\/en-or-transcribing-handwritten-text-with-python-and-azure-07-160x135.png 160w, https:\/\/carleton.ca\/xlab\/wp-content\/uploads\/en-or-transcribing-handwritten-text-with-python-and-azure-07-768x647.png 768w, https:\/\/carleton.ca\/xlab\/wp-content\/uploads\/en-or-transcribing-handwritten-text-with-python-and-azure-07-360x303.png 360w, https:\/\/carleton.ca\/xlab\/wp-content\/uploads\/en-or-transcribing-handwritten-text-with-python-and-azure-07.png 840w\" sizes=\"(max-width: 400px) 100vw, 400px\" \/><p class=\"wp-caption-text\">An image from the 1917 wartime diary of Captain William Andrew White, used in Jeff Blackadar&#8217;s Programming Historian tutorial on transcribing handwriting.<\/p><\/div>\n<div id=\"attachment_256\" class=\"wp-caption aligncenter\" style=\"width: 400px\"><img decoding=\"async\" loading=\"lazy\" class=\"size-large wp-image-256\" src=\"https:\/\/carleton.ca\/xlab\/wp-content\/uploads\/view-400x442.png\" alt=\"\" width=\"400\" height=\"442\" srcset=\"https:\/\/carleton.ca\/xlab\/wp-content\/uploads\/view-400x442.png 400w, https:\/\/carleton.ca\/xlab\/wp-content\/uploads\/view-240x265.png 240w, https:\/\/carleton.ca\/xlab\/wp-content\/uploads\/view-160x177.png 160w, https:\/\/carleton.ca\/xlab\/wp-content\/uploads\/view-768x848.png 768w, https:\/\/carleton.ca\/xlab\/wp-content\/uploads\/view-360x398.png 360w, https:\/\/carleton.ca\/xlab\/wp-content\/uploads\/view.png 1266w\" sizes=\"(max-width: 400px) 100vw, 400px\" \/><p class=\"wp-caption-text\">Transcription provided by Gemini<\/p><\/div>\n<p>Azure&#8217;s transcription, as reported in Jeff Blackadar&#8217;s Programming Historian lesson:<\/p>\n<pre class=\"highlight\"><code>DECEMBRE\r\n28 VENDREDI. Ss Innocents\r\n362-3\r\nclear and cold, - lovely out.\r\nVisit from mme Thomas D\r\nfive daughters from\r\nPontarle\u00edr.\r\nyour Doctor, Major merletti\r\narrived- good fellow\r\nNot orders to go with Capt\r\nMarrison Vit Road and 200\r\nmen to another part of\r\nFrance\r\nprote Inier\r\nSittley wip mess account\r\nCash so francs you the mouth<\/code><\/pre>\n<p><\/p>\n<p>Gemini&#8217;s transcription, via my little app:<\/p>\n<pre class=\"highlight\"><code>\r\nDECEMBRE\r\n28 VENDREDI. Ss Innocents 362-3\r\n\r\nClear and cold - lovely out.\r\nVisit from Mme Thomas &amp;\r\nfive daughters from\r\nPontarlier.\r\nNew Doctor, Major Merritt\r\narrived - good fellow.\r\nGot orders to go with Capt.\r\nMorrison (Lt-Hod) and 200\r\nmen to southern part of\r\nFrance.\r\nWrote Dyer my account -\r\nSettled up mess a\/c for the month\r\nCost 30 francs for the month\r\n\r\n<\/code><\/pre>\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>By Shawn Graham Continuing from the last experiment and ruminating on Drew Breunig&#8217;s taxonomy of use cases for AI (in short: gods, interns, cogs, and toys) as well as &#8216;homecooked software&#8216; I undertook to use Anthrophic&#8217;s &#8216;Claude&#8217; model to see what I could do. I&#8217;m building a cog via Claude&#8217;s &#8216;artifacts&#8217; feature which allows you [&hellip;]<\/p>\n","protected":false},"author":6,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_relevanssi_hide_post":"","_relevanssi_hide_content":"","_relevanssi_pin_for_all":"","_relevanssi_pin_keywords":"","_relevanssi_unpin_keywords":"","_relevanssi_related_keywords":"","_relevanssi_related_include_ids":"","_relevanssi_related_exclude_ids":"","_relevanssi_related_no_append":"","_relevanssi_related_not_related":"","_relevanssi_related_posts":"","_relevanssi_noindex_reason":"","_mi_skip_tracking":false,"_exactmetrics_sitenote_active":false,"_exactmetrics_sitenote_note":"","_exactmetrics_sitenote_category":0,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":"","_links_to":"","_links_to_target":""},"categories":[1],"tags":[68,41,97],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v21.2 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Homebrewed Software: A Handwriting Transcription App - X-Lab<\/title>\n<meta name=\"description\" content=\"By Shawn Graham Continuing from the last experiment and ruminating on Drew Breunig&#039;s taxonomy of use cases for AI (in short: gods, interns, cogs, and\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/carleton.ca\/xlab\/2024\/homebrewed-software-a-handwriting-transcription-app\/\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"shawngraham\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/carleton.ca\/xlab\/2024\/homebrewed-software-a-handwriting-transcription-app\/\",\"url\":\"https:\/\/carleton.ca\/xlab\/2024\/homebrewed-software-a-handwriting-transcription-app\/\",\"name\":\"Homebrewed Software: A Handwriting Transcription App - X-Lab\",\"isPartOf\":{\"@id\":\"https:\/\/carleton.ca\/xlab\/#website\"},\"datePublished\":\"2024-10-21T15:07:11+00:00\",\"dateModified\":\"2024-10-21T15:08:02+00:00\",\"author\":{\"@id\":\"https:\/\/carleton.ca\/xlab\/#\/schema\/person\/e8707158a71e77734ea13346b6e46feb\"},\"description\":\"By Shawn Graham Continuing from the last experiment and ruminating on Drew Breunig's taxonomy of use cases for AI (in short: gods, interns, cogs, and\",\"breadcrumb\":{\"@id\":\"https:\/\/carleton.ca\/xlab\/2024\/homebrewed-software-a-handwriting-transcription-app\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/carleton.ca\/xlab\/2024\/homebrewed-software-a-handwriting-transcription-app\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/carleton.ca\/xlab\/2024\/homebrewed-software-a-handwriting-transcription-app\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/carleton.ca\/xlab\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"News\",\"item\":\"https:\/\/carleton.ca\/xlab\/category\/news\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Homebrewed Software: A Handwriting Transcription App\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/carleton.ca\/xlab\/#website\",\"url\":\"https:\/\/carleton.ca\/xlab\/\",\"name\":\"X-Lab\",\"description\":\"Carleton University\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/carleton.ca\/xlab\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/carleton.ca\/xlab\/#\/schema\/person\/e8707158a71e77734ea13346b6e46feb\",\"name\":\"shawngraham\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/carleton.ca\/xlab\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/1b4be5c0f305aa12c7a3dd75ae5c731e?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/1b4be5c0f305aa12c7a3dd75ae5c731e?s=96&d=mm&r=g\",\"caption\":\"shawngraham\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Homebrewed Software: A Handwriting Transcription App - X-Lab","description":"By Shawn Graham Continuing from the last experiment and ruminating on Drew Breunig's taxonomy of use cases for AI (in short: gods, interns, cogs, and","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/carleton.ca\/xlab\/2024\/homebrewed-software-a-handwriting-transcription-app\/","twitter_misc":{"Written by":"shawngraham","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/carleton.ca\/xlab\/2024\/homebrewed-software-a-handwriting-transcription-app\/","url":"https:\/\/carleton.ca\/xlab\/2024\/homebrewed-software-a-handwriting-transcription-app\/","name":"Homebrewed Software: A Handwriting Transcription App - X-Lab","isPartOf":{"@id":"https:\/\/carleton.ca\/xlab\/#website"},"datePublished":"2024-10-21T15:07:11+00:00","dateModified":"2024-10-21T15:08:02+00:00","author":{"@id":"https:\/\/carleton.ca\/xlab\/#\/schema\/person\/e8707158a71e77734ea13346b6e46feb"},"description":"By Shawn Graham Continuing from the last experiment and ruminating on Drew Breunig's taxonomy of use cases for AI (in short: gods, interns, cogs, and","breadcrumb":{"@id":"https:\/\/carleton.ca\/xlab\/2024\/homebrewed-software-a-handwriting-transcription-app\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/carleton.ca\/xlab\/2024\/homebrewed-software-a-handwriting-transcription-app\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/carleton.ca\/xlab\/2024\/homebrewed-software-a-handwriting-transcription-app\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/carleton.ca\/xlab\/"},{"@type":"ListItem","position":2,"name":"News","item":"https:\/\/carleton.ca\/xlab\/category\/news\/"},{"@type":"ListItem","position":3,"name":"Homebrewed Software: A Handwriting Transcription App"}]},{"@type":"WebSite","@id":"https:\/\/carleton.ca\/xlab\/#website","url":"https:\/\/carleton.ca\/xlab\/","name":"X-Lab","description":"Carleton University","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/carleton.ca\/xlab\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/carleton.ca\/xlab\/#\/schema\/person\/e8707158a71e77734ea13346b6e46feb","name":"shawngraham","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/carleton.ca\/xlab\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/1b4be5c0f305aa12c7a3dd75ae5c731e?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/1b4be5c0f305aa12c7a3dd75ae5c731e?s=96&d=mm&r=g","caption":"shawngraham"}}]}},"acf":{"Post Thumbnail Icon":"","Post Thumbnail":false},"_links":{"self":[{"href":"https:\/\/carleton.ca\/xlab\/wp-json\/wp\/v2\/posts\/255"}],"collection":[{"href":"https:\/\/carleton.ca\/xlab\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/carleton.ca\/xlab\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/carleton.ca\/xlab\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/carleton.ca\/xlab\/wp-json\/wp\/v2\/comments?post=255"}],"version-history":[{"count":2,"href":"https:\/\/carleton.ca\/xlab\/wp-json\/wp\/v2\/posts\/255\/revisions"}],"predecessor-version":[{"id":259,"href":"https:\/\/carleton.ca\/xlab\/wp-json\/wp\/v2\/posts\/255\/revisions\/259"}],"wp:attachment":[{"href":"https:\/\/carleton.ca\/xlab\/wp-json\/wp\/v2\/media?parent=255"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/carleton.ca\/xlab\/wp-json\/wp\/v2\/categories?post=255"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/carleton.ca\/xlab\/wp-json\/wp\/v2\/tags?post=255"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}