Either the name of a language pack (for speech-to-text, transcript alignment, and so on), or the name of the base language identification feature extraction pack (for language identification tasks).
For language identification tasks, a base language identification feature extraction pack, Syls
, is provided with HPE IDOL Speech Server and is configured for use with 16k broadband data. You should not need to change this setting unless you need to use HPE IDOL Speech Server with 8k telephony data, in which case you must set Lang
to Syls-tel
.
Action: | AddTask
CheckResources ResourceSelection |
Task: | ClusterSpeech
ClusterSpeechTel ClusterSpeechToTextTel LanguageModelBuild Scorer SearchFMD SegmentText StreamToText StreamToTextMusicFilterPunct StreamToTextPunct TelWavToTextPunct TextNorm TranscriptAlign WavPhraseSearch WavToFMD WavToText WavToTextPunct |
Type: | String |
Default: | |
Example: |
NOTE:
For the ResourceSelection action, you can search using the base language code (for example, |
See Also: | Lang (configuration parameter) Model (configuration parameter) |
|