Skip to content

Latest commit

 

History

History
23 lines (20 loc) · 733 Bytes

README.md

File metadata and controls

23 lines (20 loc) · 733 Bytes

voice-note

SpeechRecognition

  • pip3 install speechrecognition
  • pip3 install pyaudio
  • pip3 installs swig
  • Microsoft Visual C++ 14.0 or greater, go to Microsoft C++ Build Tools
  • pip3 install --upgrade pocketsphinx

The Mandarin recognition accuracy is very low

Vosk (applied solution)

  • pip3 install vosk
  • pip3 install sounddevice
  • Refer to the doc
  • Download the models from here

OCR

  • pip3 install Pillow
  • pip3 install pytesseract
  • install tesseract
  • pip3 install EbookLib

UI

  • pip3 install pysimplegui