I tend to dictate a lot of reports for work into my phone first before writing them down later. However, sometimes the process of writing everything down becomes very tedious. Does anyone know a good free solution (either completely free or something that can be found on the sister site etc.)? Ideally, I would like to just let the recorded file be converted to text without having to put it through a microphone again.

 

Interesting subject and so I've found it. Thanks to you as I wouldn't know the solution to this is available as Python module. I just made a quick run and it does what it says..

I took a 2Pac in the court - YouTube as wav as input

and do a quick run, and get this output as result:

geojson io


The tutorial is from here..
Easy Speech-to-Text with Python. Speech to Text | by Dhilip Subramanian | Towards Data Science

 

I did some tinkering with it and within my limited experience in learning to program with python .. i try to script a program that will batch convert audio files to text files.. examples program in video demo .. took me about 2minutes to convert 7 .wav files on ryzen 3200g.. this script could have been better, excuse my beginnner part

here is the script:

PHP:

#####################################################################
# PROGRAM NAME: Futurewine_RockTheText.py                           #
# ABOUT: This program will batch convert audio files to text files. #
#                                                                   #
# Supported audio formats: .wav, .aiff, .aif, and .flac only        #
#                                                                   #
# Copyright (None) Free To Edit as You Like..                       #
#####################################################################

import wx as using_wx_to_run
import os as using_os_to_run
import speech_recognition as using_speech_recognition_to_run

def Get_Resources_Path():
    Create_Application = using_wx_to_run.App()
    Open_Directory_Dialog = using_wx_to_run.DirDialog(parent=None,
                            message="Import audio file(s) into project")
    Open_Directory_Dialog.ShowModal()
    Create_Application.MainLoop()
    return Open_Directory_Dialog.GetPath()

def Get_Audio_Sources(Audio_Resources_path):
    Audio_Sources = []
    Audio_Formats = [".wav", ".flac", ".aiff", ".aif", ".aifc"]
    for Audio_Source in using_os_to_run.listdir(Audio_Resources_path):
        for Audio_Format in Audio_Formats:
            if Audio_Format in Audio_Source:
                Audio_Sources.append(Audio_Source)
    return Audio_Sources

def Convert_Audio_To_Text(Audio_Sources):
    Create_Application = using_speech_recognition_to_run.Recognizer()
    for Audio_Source in Audio_Sources:
        if (".wav" in Audio_Source) or (".aif" in Audio_Source):
            Audio_Text_File = Audio_Source[:-4] + ".txt"
        else:
            Audio_Text_File = Audio_Source[:-5] + ".txt"   
        with using_speech_recognition_to_run.AudioFile(Audio_Source) as Audio:
            Audio_Transcript = Create_Application.listen(Audio)
            try:
                print("Starting out Google Speech Recognition API ..")
                print(f"Listening to {Audio_Source} ..")
                Audio_Texts = Create_Application.recognize_google(Audio_Transcript)
                print(f"Converting {Audio_Source} to {Audio_Text_File}, please wait..")
                with open (Audio_Text_File, 'w+') as Audio_Text_File_Contents:
                    for Audio_Text in Audio_Texts:
                        Audio_Text_File_Contents.write(Audio_Text)
                print(f"Finished converting {Audio_Source} to {Audio_Text_File} ..")                     
            except:
                print("Sorry.. Google Speech Recognition API is unreachable, please try again later..")             
                              
Audio_Resources_Path = Get_Resources_Path()
Audio_Sources = Get_Audio_Sources(Audio_Resources_Path)

Convert_Audio_To_Text(Audio_Sources)

How to run this script:
Using command-line and type:
> python Futurewine_RockTheText.py

Supported format: .wav, .aiff, .aif, .flac only

Program use:
Download Python | Python.org

Additional required libraries
wxPython · PyPI
SpeechRecognition · PyPI

Script attached in file.. #havefun

 

siri

 

https://audiosex.pro/threads/descript.57315