TrainedAm

DEPRECATED:

The TrainedAm parameter is deprecated in IDOL Speech Server version 11.5 and later. HPE recommends that you use the newer Deep Neural Network (DNN) techniques, rather than GMM-based acoustic models.

This parameter is still available for existing implementations, but it might be incompatible with new functionality. The parameter might be deleted in future.

An adapted acoustic model (.am file) to use instead of the language pack's default acoustic model.

You can specify an absolute or relative file path. If you specify a relative path, it is considered as being relative to the acoustic model directory. If the file path is excluded, IDOL Speech Server defaults to the acoustic model directory.

NOTE:

The TrainedAmDir parameter in the [Paths] section of the configuration file sets the location of the acoustic model directory.

Action: AddTask
CheckResources
Task: WavToText
Type: String
Default: None
Example: TrainedAm=myAcousticModel.am
See Also: AmFile (configuration parameter)

_HP_HTML5_bannerTitle.htm