{"id":13108,"date":"2023-06-01T12:43:15","date_gmt":"2023-06-01T16:43:15","guid":{"rendered":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/?p=13108"},"modified":"2023-06-01T12:43:15","modified_gmt":"2023-06-01T16:43:15","slug":"introducing-speech-to-text-text-to-speech-and-more-for-1100-languages","status":"publish","type":"post","link":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/introducing-speech-to-text-text-to-speech-and-more-for-1100-languages\/13108\/","title":{"rendered":"Introducing Speech-to-Text, Text-to-Speech, and More for 1,100+ Languages"},"content":{"rendered":"Originally published in Meta AI, May 22, 2023. Equipping machines with the ability to recognize and produce speech can make information accessible to many more people, including those who rely entirely on voice to access information. However, producing good-quality machine learning models for these tasks requires large amounts of labeled data \u2014 in this case, many thousands of hours of audio, along with transcriptions. For most languages, this data simply does not exist. For example, existing speech recognition models only cover approximately 100 languages \u2014 a fraction of the 7,000+ known languages spoken on the planet. Even more <a href=\"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/introducing-speech-to-text-text-to-speech-and-more-for-1100-languages\/13108\/\" class=\"more-link\">(more&hellip;)<\/a>","protected":false},"excerpt":{"rendered":"<p>Originally published in Meta AI, May 22, 2023. Equipping machines with the ability to recognize and produce speech can make information accessible to many more people, including those who rely entirely on voice to access information. However, producing good-quality machine learning models for these tasks requires large amounts of labeled data \u2014 in this case, [&hellip;]<\/p>\n","protected":false},"author":72,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","_links_to":"","_links_to_target":""},"categories":[11,48],"tags":[879,368,1305,791,243,8],"class_list":["post-13108","post","type-post","status-publish","format-standard","hentry","category-industry-news","category-left-hand","tag-ai","tag-artificial-intelligence","tag-deep-analytics","tag-deep-learning","tag-machine-learning","tag-predictive-analytics"],"_links":{"self":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/13108","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/users\/72"}],"replies":[{"embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/comments?post=13108"}],"version-history":[{"count":1,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/13108\/revisions"}],"predecessor-version":[{"id":13109,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/13108\/revisions\/13109"}],"wp:attachment":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/media?parent=13108"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/categories?post=13108"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/tags?post=13108"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}