Python Forum
Offline audio to text (Speech Recognition) - Printable Version

+- Python Forum (https://python-forum.io)
+-- Forum: Python Coding (https://python-forum.io/Forum-Python-Coding)
+--- Forum: Data Science (https://python-forum.io/Forum-Data-Science)
+--- Thread: Offline audio to text (Speech Recognition) (/Thread-Offline-audio-to-text-Speech-Recognition)

Pages: 1 2


RE: Offline audio to text (Speech Recognition) - wavic - Jan-16-2018

Speach recognition is not 100% accurate even if you use Google services. It will not go without editing and post-processing


RE: Offline audio to text (Speech Recognition) - jehoshua - Jan-16-2018

(Jan-16-2018, 06:16 AM)jehoshua Wrote: Following the tutorial at https://python-forum.io/Thread-Basic-Part-1-Linux-Python-3-environment?pid=18261#pid18261 , I'm not sure how to equate the following

Quote:# Make virtualenv that use Python 3.5
mint@mint ~/Desktop/my_env $ virtualenv -p /usr/bin/python3.5 my_env
mint@mint ~ $ cd my_env

for Python 3.6 ?

Have been reading up on how to use the virtual environment with Python 3.6 and python3-venv , and it seems after the initial command

python3 -m venv /home/********/Public/Servers/django-deepspeech-server
all that is required to use the virtual environment is to 'activate'

source /home/********/Public/Servers/django-deepspeech-server/bin/activate
and then to exit the virtual environment

deactivate



RE: Offline audio to text (Speech Recognition) - snippsat - Jan-16-2018

(Jan-16-2018, 11:14 AM)jehoshua Wrote: Have been reading up on how to use the virtual environment with Python 3.6 and python3-venv , and it seems after the initial command
it's just source bin/activate after you have cd into environment folder.
The deactivate to get out.
Example:
# before location 
mint@mint ~ $ which python
/home/mint/.pyenv/shims/python
mint@mint ~ $ python -V
Python 3.6.2

# Make environment and cd in
mint@mint ~ $ python -m venv foo_env
mint@mint ~ $ cd foo_env

# Activate
mint@mint ~/foo_env $ source bin/activate

# Python and pip from environment is used
(foo_env) mint@mint ~/foo_env $ which python
/home/mint/foo_env/bin/python
(foo_env) mint@mint ~/foo_env $ pip -V
pip 9.0.1 from /home/mint/foo_env/lib/python3.6/site-packages (python 3.6)

# Deactivate
(foo_env) mint@mint ~/foo_env $ deactivate
mint@mint ~/foo_env $ 



RE: Offline audio to text (Speech Recognition) - jehoshua - Jan-16-2018

(Jan-16-2018, 12:05 PM)snippsat Wrote: it's just source bin/activate after you have cd into environment folder.
The deactivate to get out.

Yes, it's either ..

source /home/********/Public/Servers/django-deepspeech-server/bin/activate
or

cd /home/********/Public/Servers/django-deepspeech-server/
source bin/activate
Thanks for your example, much appreciated. :)


RE: Offline audio to text (Speech Recognition) - jehoshua - Jan-17-2018

After a few projects were installed today, I went to test the server

$ python3 manage.py runserver
Error:
2018-01-17 08:21:49.120154: F tensorflow/core/platform/cpu_feature_guard.cc:35] The TensorFlow library was compiled to use AVX2 instructions, but these aren't available on your machine. Aborted (core dumped)
Appears a recompile is needed; not sure how to do that, however several posts on the error. One at
https://github.com/tensorflow/tensorflow/issues/6896