Voskisanofflineopensourcespeechrecognitiontoolkit.Itenablesspeechrecognitionmodelsfor18languagesanddialects-English,IndianEnglish,German,French,Spanish,Portuguese,Chinese,Russian,Turkish,Vietnamese,Italian,Dutch,Catalan,Arabic,Greek,Farsi,Filipino,Ukrainian.
Voskmodelsaresmall(50Mb)butprovidecontinuouslargevocabularytranscription,zero-latencyresponsewithstreamingAPI,reconfigurablevocabularyandspeakeridentification.
SpeechrecognitionbindingsimplementedforvariousprogramminglanguageslikePython,Java,Node.JS,C#,C++andothers.
Vosksuppliesspeechrecognitionforchatbots,smarthomeappliances,virtualassistants.Itcanalsocreatesubtitlesformovies,transcriptionforlecturesandinterviews.
VoskscalesfromsmalldeviceslikeRaspberryPiorAndroidsmartphonetobigclusters.
DocumentationForinstallationinstructions,examplesanddocumentationvisitVoskWebsite.
评论