dlpy.audio.AudioTable.load_audio_metadata¶
-
classmethod
AudioTable.load_audio_metadata(conn, path, audio_path, task='speech2text')¶ Pre-process and loads the metadata
- Parameters
- connCAS
A connection object to the current session.
- pathstring
Location to the input metadata file.
- audio_pathstring
Location to the audio files.
- taskstring, optional
Specifies the task Note: currently only support ‘speech2text’ (default)
- Returns
CASTable
- Raises
- DLPyError
If anything goes wrong, it complains and prints the appropriate message.