Speech recognition

From Media Design: Networked & Lens-Based wiki
Jump to navigation Jump to search

Ubuntu/ Mac

Requirements: Python 3.3+


  1. SpeechRecognition 3.8.1
    • pip install SpeechRecognition
    • To quickly try it out, run python -m speech_recognition after installing.
  2. PyAudio (for microphone users):
    • Install PyAudio using APT: execute sudo apt-get install python-pyaudio python3-pyaudio in a terminal.
  3. Pocketsphinx:
    1. One way:
    2. Another way (not sure if it is different or supplementary):
      • pip3 install pocketsphinx
    3. Test+Errors:
      • Try this: pocketsphinx_continuous
      • If you find this error error while loading shared libraries: libpocketsphinx.so.3: cannot open shared object file: No such file or directory do this sudo nano /etc/ld.so.conf and add
      include usr/local/lib
      include usr/
    4. Install other languages
  4. Pocketsphinx Python:
    pip install --upgrade pip setuptools wheel
    pip install --upgrade pocketsphinx
  5. Examples:
    1. Transcribe an audio file: run python3 audio_transcribe.py
    2. Save audio data to an audio file: run python3 write_audio.py


A solution:

Install Ubuntu in Windows

  • Open the start page and search for CMD (Command Prompt). Open it and type bash. Now you are in the Ubuntu environment.
  • Install git: sudo apt install git
  • Install python3:
    sudo apt-get update
    sudo apt-get install python3.6
  • Install pip:
    sudo apt-get install python-pip python-dev build-essential
    sudo pip install --upgrade pip
    sudo pip install --upgrade virtualenv
  • Install GNU make:
    sudo apt-get install build-essential
  • sudo apt install libasound-dev portaudio19-dev libportaudio2 libportaudiocpp0 ffmpeg libav-tools
  • Follow the instructions of the Ubuntu version above

B solution:

  • Install Windows SDC
  • Install Visual C++ 2015 Tools for Windows Desktop

(...needs development)


(haven't tried it) https://github.com/watsonbox/homebrew-cmu-sphinx