https://github.com/yjg30737/pyqt_speech_recognition

PyQt speech recognition demonstrating example (using pydub and speech_recognition, very easy to use)
https://github.com/yjg30737/pyqt_speech_recognition

pydub pyqt pyqt-examples pyqt-tutorial pyqt5 pyqt5-desktop-application speech-recognition speech-to-text

Last synced: 6 months ago
JSON representation

PyQt speech recognition demonstrating example (using pydub and speech_recognition, very easy to use)

Host: GitHub
URL: https://github.com/yjg30737/pyqt_speech_recognition
Owner: yjg30737
License: mit
Created: 2023-07-28T01:03:07.000Z (almost 3 years ago)
Default Branch: main
Last Pushed: 2023-08-01T00:06:30.000Z (almost 3 years ago)
Last Synced: 2024-12-29T08:42:12.619Z (over 1 year ago)
Topics: pydub, pyqt, pyqt-examples, pyqt-tutorial, pyqt5, pyqt5-desktop-application, speech-recognition, speech-to-text
Language: Python
Homepage:
Size: 120 KB
Stars: 3
Watchers: 1
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md
- License: LICENSE

README

# pyqt_speech_recognition
PyQt speech recognition demonstrating example (using pydub and speech_recognition, very easy to use)

If you want to run this one

1. git clone
2. pip install -r requirements.txt
3. python main.py

You can find out how this works in script.py as always :)

Basically we have to convert mp3 file into wav file to use speech recognition

This GUI has basic thread to run the script and label(animated loading... label) to demonstrate mp3-to-text work is processing.

## Personal memo
whisper > speech_recognition

### Reason

1. whisper is much faster than speech-recognition

2. whisper can elaborate the sentence unlike speech-recognition (such as periods, capitalization, etc.)

== wav file ==

speech_recognition
0.83
hello my dog is cute

whisper
0.56
Hello, my dog is cute.

== mp3 file ==

speech_recognition
3.3
select a memory card select a file Adventure Mode start your
adventure here

whisper
0.78
Select a memory card. Select a file. Adventure mode. Start your adventure here.