For maximum speech-to-text accuracy, you must choose the correct language pack. Select the pack based on the language and sampling rate of the audio. For the complete list of available language packs, see Available language packs.
You must configure the language pack in the [Resources]
section of the tasks configuration file. For more information, see Configure Language Packs.
When you load the language model, you can add words to the model and increase the weighting of specific words by using the ClassWordFile
parameter. You can also add or edit pronunciations by using the PronFile
parameter. For more information on these parameters and how to use them, see Load a Language Pack Manually and the IDOL Speech Server Reference.
|