Offline audio to text (Speech Recognition)

[wavic]

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

[jehoshua]

Following the tutorial at https://python-forum.io/Thread-Basic-Par...1#pid18261 , I'm not sure how to equate the following

# 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

[snippsat]

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 $ 

[jehoshua]

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. :)

[jehoshua]

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