LangId

The LangId task receives audio data from a file or binary stream and converts it into language identification features to identify the languages.

You can run this task in three modes:

Parameters

Parameter Description Required
Type The task name. Set to LangId. Yes
AppFrameDupl The balance between performance and speed for audio preprocessing DNN classification.  
AudioUpsampling Whether to allow audio upsampling if the input audio has a sample rate too low for the task.  
Beam The beam width of the search process.  
ClassList A list of language classifiers to use.  
ClassPath The path to the directory containing the language classifiers.  
ClosedSet Whether to use closed set or open set language identification.  
DiagFile The file to write the diagnostic information to.  
DiagLevel The level of detail to include in the diagnostic information.  
DiscardShort The minimum segment length to allow (when LidMode is Boundary).  
EndTime The end of an audio section to process.  
File The audio file to process. Yes, if InputType is File.
FrameDupl An integer value which allows for greater time efficiency with only a minimal loss of recognition accuracy.  
InputType The type of audio to process (file, binary data, or stream).  
Lang The name of the language pack to use.  
LangList A subset of languages to use from the classifier list file.  
LidMode The mode to use for language identification.  
MaxPhoneLen The maximum phoneme length to allow (in seconds).  
MinPhoneRate The minimum phoneme rate (phonemes per second).  
MinPhones The minimum number of phonemes per segment.  
NBest The maximum number of language candidates to include in the output file.  
Out The file to write language identification results to.  
ScoreMode The scoring method to use for speaker identification.  
SegSize The maximum results segment size.  
StartTime The beginning of an audio section to process.  
SugdInputChannels The channel layout of the input media file. This parameter does not apply when InputType is Stream.  
SugdInputFrequency The sampling rate of the input media file. This parameter does not apply when InputType is Stream.  
NOTE:

The ClassList parameter is required only if you want to change the audio sample rate, or if you want to use your own custom classifiers. You might also need to specify the ClassPath parameter, depending on the location of the classifier files.

Examples

Segmented Mode

http://localhost:15000/action=AddTask&Type=LangId&LidMode=segmented&InputType=Stream&Out=SpeechLang6.ctm

This action identifies languages in the audio stream using the default language classifiers, and writes the identification results to the SpeechLang6.ctm file.

http://localhost:15000/action=AddTask&Type=LangId&LidMode=segmented&File=C:\Data\Speech.wav

This action identifies the language in the Speech.wav file using the default language classifiers.

Cumulative Mode

http://localhost:15000/action=AddTask&Type=LangId&LidMode=cumulative&InputType=Stream&Out=SpeechLang3.ctm

This action identifies the language in the audio stream using the default language classifiers and writes the identification results to the SpeechLang3.ctm file.

http://localhost:15000/action=AddTask&Type=LangId&LidMode=cumulative&File=C:\Data\Speech.wav&Out=SpeechLang4.ctm

This action identifies the language in the Speech.wav file using the default language classifiers and writes the identification results to the SpeechLang4.ctm file.

Boundary Mode

http://localhost:15000/action=AddTask&Type=LangId&LidMode=boundary&InputType=Stream&ClassList=ListManager/OptClassSet&ClassPath=C:\LangID\&Out=SpeechLang1.ctm

This action identifies languages and language boundaries in the audio stream using the language classifiers specified in the OptClassSet list and writes the identification results to the SpeechLang1.ctm file.

http://localhost:15000/action=AddTask&Type=LangId&Lidmode=boundary&File=C:\Data\Speech.wav

This action identifies languages and language boundaries in the Speech.wav file using the default language classifiers.


_FT_HTML5_bannerTitle.htm