{"id":1571,"date":"2018-12-09T16:37:47","date_gmt":"2018-12-09T16:37:47","guid":{"rendered":"http:\/\/demensdeum.com\/blog\/?p=1571"},"modified":"2024-12-16T22:32:41","modified_gmt":"2024-12-16T19:32:41","slug":"textgenrnn","status":"publish","type":"post","link":"https:\/\/demensdeum.com\/blog\/hi\/2018\/12\/09\/textgenrnn\/","title":{"rendered":"Tesla speaking"},"content":{"rendered":"<p>In this post I will describe the process of creating a <a rel=\"noreferrer noopener\" href=\"https:\/\/twitter.com\/deepnnquotes\" target=\"_blank\">quote generator<\/a>.<\/p>\n<h4 class=\"wp-block-heading\">TL;DR<\/h4>\n<p>For training and text generation &#8211; use the library <a rel=\"noreferrer noopener\" aria-label=\"For training and text generation - use the textgenrnn library, for filtering phrases you need to use spell checking with the hunspell utility and its library for C\/python. After training in Cola(opens in a new tab)\" href=\"https:\/\/github.com\/minimaxir\/textgenrnn\" target=\"_blank\">textgenrnn<\/a>, to filter phrases you need to use spell checking with the utility <a rel=\"noreferrer noopener\" aria-label=\"For training and text generation - use the textgenrnn library, to filter phrases you need to use spell checking with the hunspell utility and its library for C\/python. After training in Cola(opens in a new tab)\" href=\"http:\/\/hunspell.github.io\/\" target=\"_blank\">hunspell<\/a> and its C\/python library. After training in <a rel=\"noreferrer noopener\" aria-label=\"For training and text generation - use the textgenrnn library, to filter phrases you need to use spell checking with the hunspell utility and its C\/python library. After training in Colaboratory, you can start generating text. About 90% of the text will be completely unreadable, but the remaining 10% will contain a bit of meaning, and with manual processing the phrases will look quite good. (opens in a new tab)\" href=\"https:\/\/colab.research.google.com\/\" target=\"_blank\">Colaboratory<\/a>, you can start generating text. About 90% of the text will be completely unreadable, but the remaining 10% will contain a bit of meaning, and with manual refinement, the phrases will look quite good.<br \/>The easiest way to run a ready-made neural network is in Colaboratory:<br \/><a href=\"https:\/\/colab.research.google.com\/drive\/1-wbZMmxvsm3SoclJv11villo9VbUesbc\" target=\"_blank\" rel=\"noreferrer noopener\" aria-label=\"For training and text generation, use the textgenrnn library, to filter phrases, you need to use spell checking using the hunspell utility and its library for C \/ python. After training in Colaboratory, you can start generating text. About 90% of the text will be completely unreadable, but the remaining 10% will contain a bit of meaning, and with manual editing the phrases will look quite good.The easiest way to launch a ready-made neural network is in Colaboratory:<a href=\"https:\/\/colab.research.google.com\/drive\/1-wbZMmxvsm3SoclJv11villo9VbUesbc\" rel=\"noopener\" target=\"_blank\">https:\/\/colab.research.google.com\/drive\/1-wbZMmxvsm3SoclJv11villo9VbUesbc<\/a>(opens in a new tab)&#8221;>https:\/\/colab.research.google.com\/drive\/1-wbZMmxvsm3SoclJv11villo9VbUesbc<\/a><\/p>\n<h4 class=\"wp-block-heading\">Source code<br \/><\/h4>\n<p><a href=\"https:\/\/gitlab.com\/demensdeum\/MachineLearning\/tree\/master\/3quotesGenerator\" target=\"_blank\" rel=\"noreferrer noopener\" aria-label=\"https:\/\/gitlab.com\/ demensdeum\/MachineLearning\/tree\/master\/3quotesGenerator (opens in a new tab)\">https:\/\/gitlab.com\/demensdeum\/MachineLearning\/tree\/master\/3quotesGenerator<\/a><\/p>\n<h4 class=\"wp-block-heading\">Sources<br \/><\/h4>\n<p><a rel=\"noreferrer noopener\" aria-label=\"https:\/\/minimaxir.com\/2018\/05\/text-neural-networks\/<a href=\"https:\/\/karpathy.github.io\/2015\/05\/21\/rnn-effectiveness\/\" rel=\"noopener\" target=\"_blank\">https:\/\/karpathy.github.io\/2015\/05\/21\/rnn-effectiveness\/<\/a><a href=\"https:\/\/medium.com\/deep-learning-turkey\/google-colab-free-gpu-tutorial-e113627b9f5d\" rel=\"noopener\" target=\"_blank\">https:\/\/medium.com\/deep-learning-turkey\/google-colab-free-gpu-tutorial-e113627b9f5d<\/a><a href=\"https:\/\/github.com\/wooorm\/dictionaries (opens in a new tab)\" href=\"https:\/\/minimaxir.com\/2018\/05\/text-neural-networks\/\" target=\"_blank\">https:\/\/minimaxir.com\/2018\/05\/text-neural-networks\/<\/a><br \/><a rel=\"noreferrer noopener\" aria-label=\"https:\/\/minimaxir.com\/2018\/05\/text-neural-networks\/\" rel=\"noopener\" target=\"_blank\">https:\/\/github.com\/wooorm\/dictionaries (opens in a new tab)&#8221; href=&#8221;https:\/\/minimaxir.com\/2018\/05\/text-neural-networks\/&#8221; target=&#8221;_blank&#8221;>https:\/\/minimaxir.com\/2018\/05\/text-neural-networks\/<\/a><br \/><a rel=\"noreferrer noopener\" aria-label=\"https:\/\/minimaxir.com\/2018\/05\/text-neural-networks\/<\/a><a href=\"https:\/\/karpathy.github.io\/2015\/05\/21\/rnn-effectiveness\/ (opens in a new tab)\" href=\"https:\/\/karpathy.github.io\/2015\/05\/21\/rnn-effectiveness\/\" target=\"_blank\">https:\/\/karpathy.github.io\/2015\/05\/21\/rnn-effectiveness\/<\/a><br \/><a href=\"https:\/\/medium.com\/deep-learning-turkey\/google-colab-free-gpu-tutorial-e113627b9f5d\">https:\/\/medium.com\/deep-learning-turkey\/google-colab-free-gpu-tutorial-e113627b9f5d<\/a><br \/><a href=\"https:\/\/github.com\/wooorm\/dictionaries\" target=\"_blank\" rel=\"noreferrer noopener\" aria-label=\"https:\/\/minimaxir.com\/2018\/05\/text-neural-networks\/\" rel=\"noopener\" target=\"_blank\">https:\/\/karpathy.github.io\/2015\/05\/21\/rnn-effectiveness\/ (opens in a new tab)&#8221; href=&#8221;https:\/\/karpathy.github.io\/2015\/05\/21\/rnn-effectiveness\/&#8221; target=&#8221;_blank&#8221;>https:\/\/karpathy.github.io\/2015\/05\/21\/rnn-effectiveness\/<\/a><br \/><a href=\"https:\/\/medium.com\/deep-learning-turkey\/google-colab-free-gpu-tutorial-e113627b9f5d\">https:\/\/medium.com\/deep-learning-turkey\/google-colab-free-gpu-tutorial-e113627b9f5d<\/a><br \/><a href=\"https:\/\/github.com\/wooorm\/dictionaries\" target=\"_blank\" rel=\"noreferrer noopener\" aria-label=\"https:\/\/minimaxir.com\/2018\/05\/text-neural-networks\/<\/a><a href=\"https:\/\/karpathy.github.io\/2015\/05\/21\/rnn-effectiveness\/\" rel=\"noopener\" target=\"_blank\">https:\/\/karpathy.github.io\/2015\/05\/21\/rnn-effectiveness\/<\/a><a href=\"https:\/\/medium.com\/deep-learning-turkey\/google-colab-free-gpu-tutorial-e113627b9f5d\" rel=\"noopener\" target=\"_blank\">https:\/\/medium.com\/deep-learning-turkey\/google-colab-free-gpu-tutorial-e113627b9f5d<\/a><a href=\"https:\/\/github.com\/wooorm\/dictionaries (opens in a new tab)\">https:\/\/github.com\/wooorm\/dictionaries<\/a><\/p>\n<p>&#8221; rel=&#8221;noopener&#8221; target=&#8221;_blank&#8221;>https:\/\/github.com\/wooorm\/dictionaries (opens in a new tab)&#8221;>https:\/\/github.com\/wooorm\/dictionaries<\/a><\/p>\n<p><\/a><\/p>\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>In this post I will describe the process of creating a quote generator. TL;DR For training and text generation &#8211; use the library textgenrnn, to filter phrases you need to use spell checking with the utility hunspell and its C\/python library. After training in Colaboratory, you can start generating text. About 90% of the text<a class=\"more-link\" href=\"https:\/\/demensdeum.com\/blog\/hi\/2018\/12\/09\/textgenrnn\/\">Continue reading <span class=\"screen-reader-text\">&#8220;Tesla speaking&#8221;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[61],"tags":[93],"class_list":["post-1571","post","type-post","status-publish","format-standard","hentry","category-techie","tag-deep-learning","entry"],"translation":{"provider":"WPGlobus","version":"3.0.2","language":"hi","enabled_languages":["en","ru","zh","de","fr","ja","pt","hi"],"languages":{"en":{"title":true,"content":true,"excerpt":false},"ru":{"title":true,"content":true,"excerpt":false},"zh":{"title":true,"content":true,"excerpt":false},"de":{"title":true,"content":true,"excerpt":false},"fr":{"title":true,"content":true,"excerpt":false},"ja":{"title":true,"content":true,"excerpt":false},"pt":{"title":true,"content":true,"excerpt":false},"hi":{"title":false,"content":false,"excerpt":false}}},"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/demensdeum.com\/blog\/hi\/wp-json\/wp\/v2\/posts\/1571","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/demensdeum.com\/blog\/hi\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/demensdeum.com\/blog\/hi\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/demensdeum.com\/blog\/hi\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/demensdeum.com\/blog\/hi\/wp-json\/wp\/v2\/comments?post=1571"}],"version-history":[{"count":15,"href":"https:\/\/demensdeum.com\/blog\/hi\/wp-json\/wp\/v2\/posts\/1571\/revisions"}],"predecessor-version":[{"id":3968,"href":"https:\/\/demensdeum.com\/blog\/hi\/wp-json\/wp\/v2\/posts\/1571\/revisions\/3968"}],"wp:attachment":[{"href":"https:\/\/demensdeum.com\/blog\/hi\/wp-json\/wp\/v2\/media?parent=1571"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/demensdeum.com\/blog\/hi\/wp-json\/wp\/v2\/categories?post=1571"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/demensdeum.com\/blog\/hi\/wp-json\/wp\/v2\/tags?post=1571"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}