speech_recognition
Classes | Functions
prepare Namespace Reference

Classes

class  DataPreparation
 
class  Flags
 
class  Index
 

Functions

def main ()
 

Detailed Description

This module has been written to prepare the files and directory structure
required by Kaldi-ASR to develop Acoustic Models.

Structure of the CSV file:

-----------------------------------------------------------------
| SPEAKER_ID | UTTERANCE_ID | WAV_PATH | TRANSCRIPTION | GENDER |
-----------------------------------------------------------------

TODO:
1. Check correctness of file endings for each created data file
2. Analyse the best suited format for value of fields SPEAKER_ID and UTTERANCE_ID.
   Change the following methods accordingly:
a. text
b. wav.scp
c. spk2utt
d. utt2spk
3. Analyse the best suited naming structure for each FILE

Function Documentation

◆ main()

def prepare.main ( )
When script is executed as __main__:

Args:
    param1 (str): Absolute path of the CSV metadata file
    param2 (str): Absolute path of the root directory of Speech Recognition System
    param3 (str): Type of Dataset

Definition at line 417 of file prepare.py.