FAVE TranscriptProcessor module

Functions for processing FAAV transcripts

class fave.align.transcriptprocessor.TranscriptProcessor(transript_file, pronunciation_dictionary, *args, **kwargs)

Wrapper for handling tab delimited FAAV transcription files

check_dictionary_entries(wavfile)

checks that all words in lines have an entry in the CMU dictionary; if not, prompts user for Arpabet transcription and adds it to the dict file. If “check transcription” option is selected, writes list of unknown words to file and exits.

check_transcription_file()

checks the format of the input transcription file and returns a list of empty lines to be deleted from the input

static check_transcription_format(line)

checks that input format of transcription file is correct (5 tab-delimited data fields)

preprocess_transcription(line)

preprocesses transcription input for CMU dictionary lookup and forced alignment

read_transcription_file()

Reads file into memory

static replace_smart_quotes(all_input)

Replace fancy quotes with straight quotes