Speech recognition: Difference between revisions
No edit summary |
No edit summary |
||
| Line 5: | Line 5: | ||
https://pypi.python.org/pypi/SpeechRecognition | https://pypi.python.org/pypi/SpeechRecognition | ||
# SpeechRecognition 3.8.1 | # SpeechRecognition 3.8.1 | ||
#*<small> | #*<small>pip install SpeechRecognition</small> | ||
#*To quickly try it out, run <small>python -m speech_recognition</small> after installing. | #*To quickly try it out, run <small>python -m speech_recognition</small> after installing. | ||
# PyAudio (for microphone users): | # PyAudio (for microphone users): | ||
#*Install PyAudio using APT: execute <small>sudo apt-get install python-pyaudio python3-pyaudio</small> in a terminal. | #*Install PyAudio using APT: execute <small>sudo apt-get install python-pyaudio python3-pyaudio</small> in a terminal. | ||
# Pocketsphinx: | # Pocketsphinx: | ||
## One way: | |||
##*install dependencies: <small>sudo apt-get install gcc automake autoconf libtool bison swig python-dev libpulse-dev</small> | |||
##*Follow the instructions: https://bangladroid.wordpress.com/2017/02/16/installing-cmu-sphinx-on-ubuntu/ | |||
## Another way (not sure if it is different or supplementary): | ## Another way (not sure if it is different or supplementary): | ||
##*<small>pip3 install pocketsphinx</small> | ##*<small>pip3 install pocketsphinx</small> | ||
| Line 19: | Line 22: | ||
##[https://github.com/Uberi/speech_recognition/blob/master/reference/pocketsphinx.rst Install other languages] | ##[https://github.com/Uberi/speech_recognition/blob/master/reference/pocketsphinx.rst Install other languages] | ||
# [https://github.com/bambocher/pocketsphinx-python Pocketsphinx Python]: | # [https://github.com/bambocher/pocketsphinx-python Pocketsphinx Python]: | ||
#:<small> | #:<small>pip install --upgrade pip setuptools wheel</small> | ||
#:<small> | #:<small>pip install --upgrade pocketsphinx</small> | ||
# Examples: | # Examples: | ||
## Transcribe an audio file: run <small>python3 [https://github.com/Uberi/speech_recognition/blob/master/examples/audio_transcribe.py audio_transcribe.py]</small> | ## Transcribe an audio file: run <small>python3 [https://github.com/Uberi/speech_recognition/blob/master/examples/audio_transcribe.py audio_transcribe.py]</small> | ||
## Save audio data to an audio file: run <small>python3 [https://github.com/Uberi/speech_recognition/blob/master/examples/write_audio.py write_audio.py]</small> | ## Save audio data to an audio file: run <small>python3 [https://github.com/Uberi/speech_recognition/blob/master/examples/write_audio.py write_audio.py]</small> | ||
Revision as of 17:12, 23 March 2018
For Ubuntu:
Requirements: Python2.6, 2.7, or 3.3+
https://pypi.python.org/pypi/SpeechRecognition
- SpeechRecognition 3.8.1
- pip install SpeechRecognition
- To quickly try it out, run python -m speech_recognition after installing.
- PyAudio (for microphone users):
- Install PyAudio using APT: execute sudo apt-get install python-pyaudio python3-pyaudio in a terminal.
- Pocketsphinx:
- One way:
- install dependencies: sudo apt-get install gcc automake autoconf libtool bison swig python-dev libpulse-dev
- Follow the instructions: https://bangladroid.wordpress.com/2017/02/16/installing-cmu-sphinx-on-ubuntu/
- Another way (not sure if it is different or supplementary):
- pip3 install pocketsphinx
- 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/
- Install other languages
- One way:
- Pocketsphinx Python:
- pip install --upgrade pip setuptools wheel
- pip install --upgrade pocketsphinx
- Examples:
- Transcribe an audio file: run python3 audio_transcribe.py
- Save audio data to an audio file: run python3 write_audio.py