Hello everyone.
Is it possible to use pocketsphinx to recognize speech directly from microphone. I've found an example of python script here http://blog.justsophie.com/python-speech-to-text-with-pocketsphinx/. This script creates a file and waits writes the recording of the void into this file. After that files transfers to recognition engine and I see on the console the result of recognition.
Does engine work without files (direct recognition of words from microphone)?
Also I have a question about some documentation for a sphinxbase5 and pocketsphinx5. Do you have such documentation (I've seen the doxygen generated docs but it doesn't give me a needed information).
Thanks in advance.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hello everyone.
Is it possible to use pocketsphinx to recognize speech directly from microphone. I've found an example of python script here http://blog.justsophie.com/python-speech-to-text-with-pocketsphinx/. This script creates a file and waits writes the recording of the void into this file. After that files transfers to recognition engine and I see on the console the result of recognition.
Does engine work without files (direct recognition of words from microphone)?
Also I have a question about some documentation for a sphinxbase5 and pocketsphinx5. Do you have such documentation (I've seen the doxygen generated docs but it doesn't give me a needed information).
Thanks in advance.
There are many examples in
https://github.com/cmusphinx/pocketsphinx/blob/master/swig/python/test
For example you can study
https://github.com/cmusphinx/pocketsphinx/blob/master/swig/python/test/kws_test.py
or https://github.com/cmusphinx/pocketsphinx/blob/master/swig/python/test/continuous_test.py