<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>nltk on A Tinkerer&#39;s Canvas</title>
    <link>https://anuran-roy.github.io/tags/nltk/</link>
    <description>Recent content in nltk on A Tinkerer&#39;s Canvas</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Sat, 24 Jul 2021 20:43:12 +0530</lastBuildDate><atom:link href="https://anuran-roy.github.io/tags/nltk/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Offline Speech Recognition with Vosk</title>
      <link>https://anuran-roy.github.io/post/blog/offline-speech-with-vosk/</link>
      <pubDate>Sat, 24 Jul 2021 20:43:12 +0530</pubDate>
      
      <guid>https://anuran-roy.github.io/post/blog/offline-speech-with-vosk/</guid>
      <description>No more Sphinx The long-lived and long-loved CMU Sphinx, a brainchild of Carnegie Mellon University, is not maintained actively anymore, since 5 years. But does that mean that we need to move to more production-oriented solutions? No, we actually don&amp;rsquo;t. The team CMU Sphinx Project has slowly rolled in a new child project - Vosk.
Note that there are many other production-oriented solutions available (like OpenVINO, Mozilla DeepSpeech, etc.), which are equally as good, if not better at speech recognition.</description>
    </item>
    
  </channel>
</rss>
