Unable to install deepspeech on centos 6 9

[JRMeyer]

>>> ajayks5017
[February 26, 2018, 10:06am]

Hello, slash
Greetings!

I am new to DeepSpeech and trying to prepare the setup for deepSpeech. slash
I am facing below issue-

(deepspeech-venv) slash [root slash localhost DeepSpeech slash ] slash # pip install
deepspeech slash
Collecting deepspeech slash
/root/tmp/deepspeech-venv/lib/python2.7/site-packages/pip/vendor/requests/packages/urllib3/util/ssl.py:318:
SNIMissingWarning: An HTTPS request has been made, but the SNI (Subject
Name Indication) extension to TLS is not available on this platform.
This may cause the server to present an incorrect TLS certificate, which
can cause validation failures. You can upgrade to a newer version of
Python to solve this. For more information, see
#snimissingwarning>. slash
SNIMissingWarning slash
/root/tmp/deepspeech-venv/lib/python2.7/site-packages/pip/vendor/requests/packages/urllib3/util/ssl.py:122:
InsecurePlatformWarning: A true SSLContext object is not available. This
prevents urllib3 from configuring SSL appropriately and may cause
certain SSL connections to fail. You can upgrade to a newer version of
Python to solve this. For more information, see
#insecureplatformwarning>. slash
InsecurePlatformWarning slash
Could not find a version that satisfies the requirement deepspeech
(from versions: ) slash
No matching distribution found for deepspeech

I am following below link for installation slash

github.com

#### mozilla/DeepSpeech/blob/master/README.md

# Project DeepSpeech

Project DeepSpeech is an open source Speech-To-Text engine, using a model trained by machine learning techniques, based on Baidu's Deep Speech research paper. Project DeepSpeech uses Google's TensorFlow project to make the implementation easier.



Pre-built binaries that can be used for performing inference with a trained model can be installed with pip. Proper setup using virtual environment is recommended and you can find that documented below.

A pre-trained English model is available for use, and can be downloaded using the instructions below.

Once everything is installed you can then use the deepspeech binary to do speech-to-text on short, approximately 5 second, audio files (currently only WAVE files with 16-bit, 16 kHz, mono are supported in the Python client):

bash<br/> pip install deepspeech<br/> deepspeech models/output_graph.pb models/alphabet.txt my_audio_file.wav<br/>

This file has been truncated. show
original

Below is the system info slash
(deepspeech-venv) slash [root slash localhost DeepSpeech slash ] slash # python slash --version slash
Python 2.7.6 slash
You have mail in /var/spool/mail/centerstage slash
(deepspeech-venv) slash [root slash localhost DeepSpeech slash ] slash # cat
/etc/redhat-release slash
CentOS release 6.9 (Final)

Please let me know what is the problem here? Why I am not able to
install deepspeech.

[This is an archived TTS discussion thread from discourse.mozilla.org/t/unable-to-install-deepspeech-on-centos-6-9]

[JRMeyer]

>>> lissyx
[February 26, 2018, 10:06am]

Please try pip install --verbose deepspeech and paste the content.
Also, i'd advise against installing as root, that's not a good habit to
take.

Also, what is your pip version? Try pip --version, you might need
something 9.x. In this case, try pip install --upgrade --user pip, and
use the slash $HOME/.local/bin/pip

[Archived Post]

[JRMeyer]

>>> ajayks5017
[February 26, 2018, 5:57pm]

Hello Lissyx,

Thanks for the response!

My pip version is 9.0.1 slash
(deepspeech-venv) slash [centerstage slash localhost DeepSpeech slash ] slash $ pip
slash --version slash
pip 9.0.1 from
/home/centerstage/tmp/deepspeech-venv/lib/python2.7/site-packages
(python 2.7)

Output of 'pip install slash --verbose deepspeech' command is in the attached
file- slash
The output of this command is too long and I am neither able to paste
that nor upload as a doc here. As this system reports error that new
user can only put 5 links in a post. Can you suggest me how to upload
it?

[Archived Post]

[JRMeyer]

>>> lissyx
[February 26, 2018, 6:04pm]

pastebin.mozilla.org ?

[Archived Post]

[JRMeyer]

>>> ajayks5017
[February 27, 2018, 3:13am]

Thanks Lissyx!

Please find the link below containing the output of 'pip install
slash --verbose deepspeech' command. slash
https://pastebin.mozilla.org/9078682

I am now not working as a root user as well.

Thanks!

[Archived Post]

[JRMeyer]

>>> lissyx
[February 27, 2018, 9:13am]

Okay, can you try this?

$ wget https://pypi.python.org/packages/45/45/6f153f51407486d541723620bcec68f942236692c5fcd328e7dac5301ca1/deepspeech-0.1.1-cp27-cp27mu-manylinux1_x86_64.whl && mv deepspeech-0.1.1-cp27-cp27m-manylinux1_x86_64.whl && pip install --user --upgrade deepspeech-0.1.1-cp27-cp27m-manylinux1_x86_64.whl

I'm wondering if there's a slight difference with your Python version?

[Archived Post]

[JRMeyer]

>>> lissyx
[February 27, 2018, 9:32am]

Can you run this as well?

python -c 'import sysconfig; import pprint; pprint.pprint(sysconfig.get_config_vars())'

[Archived Post]

[JRMeyer]

>>> priyanka
[February 27, 2018, 9:49am]

hello, everyone I am trying to run deepspeech on ubuntu and getting this
error slash

How to resolve this?

[Archived Post]

[JRMeyer]

>>> ajayks5017
[February 27, 2018, 9:53am]

Hello Lissyx,

On applying upgrade command it shows below output-

(deepspeech-venv) slash [centerstage slash localhost DeepSpeech slash ] slash $ pip install
slash --upgrade deepspeech-0.1.1-cp27-cp27mu-manylinux1_x86_64.whl slash
deepspeech-0.1.1-cp27-cp27mu-manylinux1_x86_64.whl is not a supported
wheel on this platform.

On running slash
(deepspeech-venv) slash [centerstage slash localhost DeepSpeech slash ] slash $ python -c
'import sysconfig; import pprint;
pprint.pprint(sysconfig.get_config_vars())'

I got below output and this time also not able to install deepspeech. slash
https://pastebin.mozilla.org/9078692

[Archived Post]

[JRMeyer]

>>> lissyx
[February 27, 2018, 9:55am]

Looks like I missed one part of the command:
mv deepspeech-0.1.1-cp27-cp27mu-manylinux1_x86_64.whl deepspeech-0.1.1-cp27-cp27m-manylinux1_x86_64.whl && pip install --user --upgrade deepspeech-0.1.1-cp27-cp27m-manylinux1_x86_64.whl

[Archived Post]

[JRMeyer]

>>> lissyx
[February 27, 2018, 9:58am]

Right, this might be the lack of --enable-unicode=ucs4 in the
CONFIG_ARGS parts. If that's the case, renaming to
deepspeech-0.1.1-cp27-cp27m-manylinux1_x86_64.whl should trick it, but
it might behave erratically with Unicode.

It could be useful that you file an issue on Github about supporting
this setup :).

[Archived Post]

[JRMeyer]

>>> ajayks5017
[February 27, 2018, 11:52am]

Hello lissyx, slash
Thanks for the response!

Now I am able to install deepspeech. slash
But when I tried to install the requirements it throws error while
installing tensorflow-1.5.0

(deepspeech-venv) slash [centerstage slash localhost DeepSpeech slash ] slash $ pip install -r
requirements.txt slash
Collecting pandas (from -r requirements.txt (line 1)) slash
/home/centerstage/tmp/deepspeech-venv/lib/python2.7/site-packages/pip/vendor/requests/packages/urllib3/util/ssl.py:318:
SNIMissingWarning: An HTTPS request has been made, but the SNI (Subject
Name Indication) extension to TLS is not available on this platform.
This may cause the server to present an incorrect TLS certificate, which
can cause validation failures. You can upgrade to a newer version of
Python to solve this. For more information, see
#snimissingwarning>. slash
SNIMissingWarning slash
/home/centerstage/tmp/deepspeech-venv/lib/python2.7/site-packages/pip/vendor/requests/packages/urllib3/util/ssl.py:122:
InsecurePlatformWarning: A true SSLContext object is not available. This
prevents urllib3 from configuring SSL appropriately and may cause
certain SSL connections to fail. You can upgrade to a newer version of
Python to solve this. For more information, see
#insecureplatformwarning>. slash
InsecurePlatformWarning slash
Using cached pandas-0.22.0.tar.gz slash
Collecting progressbar2 (from -r requirements.txt (line 2)) slash
Using cached progressbar2-3.35.2-py2.py3-none-any.whl slash
Collecting python-utils (from -r requirements.txt (line 3)) slash
Using cached python_utils-2.3.0-py2.py3-none-any.whl slash
Collecting tensorflow==1.5.0 (from -r requirements.txt (line 4)) slash
slash DEEPSPEECH.cdx deepspeech.commands DEEPSPEECH.pages DEEPSPEECH.warc.gz discourse.mozilla.org html-to-markdown.sh shell-conver-html-to-split-posts.sh sorted-deepspeech-posts slash DEEPSPEECH.cdx deepspeech.commands DEEPSPEECH.pages DEEPSPEECH.warc.gz discourse.mozilla.org html-to-markdown.sh shell-conver-html-to-split-posts.sh sorted-deepspeech-posts Could not find a version that satisfies the requirement
tensorflow==1.5.0 (from -r requirements.txt (line 4)) (from versions:
slash DEEPSPEECH.cdx deepspeech.commands DEEPSPEECH.pages DEEPSPEECH.warc.gz discourse.mozilla.org html-to-markdown.sh shell-conver-html-to-split-posts.sh sorted-deepspeech-posts slash DEEPSPEECH.cdx deepspeech.commands DEEPSPEECH.pages DEEPSPEECH.warc.gz discourse.mozilla.org html-to-markdown.sh shell-conver-html-to-split-posts.sh sorted-deepspeech-posts slash
No matching distribution found for tensorflow==1.5.0 (from -r
requirements.txt (line 4))

Meanwhile I just switched to Centos version 7.3 and I am able to
successfully setup the deepspeech project along with tensorflow.

[Archived Post]

[JRMeyer]

>>> lissyx
[February 27, 2018, 12:13pm]

This is only needed if you intend to train. The fact that you have been
able to install confirms it was just the unicode stuff. But if
TensorFlow upstream itself fails, then all the bets are off and we
cannot help you on that.

[Archived Post]

[JRMeyer]

>>> ajayks5017
[February 27, 2018, 12:25pm]

Hello Lissyx,

Thanks for your help and the quick responses!!

I have a question and please let me know if this is the right place to
ask it or should I open a new discussion window for it?

When I ran the decoder using the default model on a audio .wav file of
slash ~4 sec it took slash ~38 sec of inference time.

(deepspeech-venv) slash [centerstage slash localhost DeepSpeech slash ] slash $ deepspeech
.../models/output_graph.pb .../hiroshima-1.wav .../models/alphabet.txt
.../models/lm.binary .../models/trie slash
Loading model from file .../models/output_graph.pb slash
2018-02-27 17:26:13.741657: I
tensorflow/core/platform/cpu_feature_guard.cc:137 slash ] Your CPU supports
instructions that this TensorFlow binary was not compiled to use: AVX2
FMA slash
Loaded model in 0.469s. slash
Loading language model from files .../models/lm.binary .../models/trie slash
Loaded language model in 2.297s. slash
Running inference. slash
on a bright cloud less morning slash
Inference took 38.391s for 4.620s audio file.

Why is it taking this long of time? slash
How to improve the speed?

[Archived Post]

[JRMeyer]

>>> lissyx
[February 27, 2018, 12:56pm]

It depends on a lot of parameters: CPU, IO subsystem. Can you give more
details ?

[Archived Post]

[JRMeyer]

>>> ajayks5017
[February 27, 2018, 1:22pm]

Hi Lissyx,

Below are the output of top/iostat commands while the deepspeech binary
is decoding the slash ~4 sec audio file.

1. Working on 12 CPU machine

top - 18:04:49 up 39 days, 2:50, 11 users, load average: 2.27, 1.64,
0.98 slash
Tasks: 1 total, 0 running, 1 sleeping, 0 stopped, 0 zombie slash
%Cpu(s): 17.0 us, 0.3 sy, 0.0 ni, 82.7 id, 0.0 wa, 0.0 hi, 0.0 si, 0.0
st slash
KiB Mem : 15688592 total, 2214132 free, 3858156 used, 9616304
buff/cache slash
KiB Swap: 16383996 total, 15744108 free, 639888 used. 10986616 avail Mem

PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND slash
1344 centers+ 20 0 5362376 2.740g 1.519g S 201.0 18.3 0:57.56 deepspeech

2. CentOS Linux release 7.3.1611 (Core)

3. iostat output while the deepspeech binary system is running

slash [root slash localhost DeepSpeech slash ] slash # iostat slash
Linux 3.10.0-514.26.2.el7.x86_64 (localhost.localdomain) Tuesday 27
February 2018 x86_64 (12 CPU)

avg-cpu: %user %nice %system %iowait %steal %idle slash
1.55 0.00 0.51 0.08 0.00 97.86

Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn slash
sda 1.61 0.82 38.20 2763476 129148525

Please let me know if you need any more information.

[Archived Post]

[JRMeyer]

>>> lissyx
[February 27, 2018, 1:43pm]

What's your exact CPU model, amount of RAM ? Hard-drive or SSD? It could
the loading of the model itself that takes some time. Try artifacts from
TaskCluster on master branch, C++ client in native_client.tar.xz
contains '-t' option and you can use the mmap trick. It should all be
accessible from readme. I'll give you direct pointers if you don't find
but right now I cannot :-/.

[Archived Post]

[JRMeyer]

>>> ajayks5017
[March 1, 2018, 9:03am]

Hello Lissyx,

I have downloaded DeepSpeech from below link and installed for python
using the README.md file present in Deepspeech directory slash

{.site-icon width='32'

### mozilla/DeepSpeech

A TensorFlow implementation of Baidu slash 's DeepSpeech architecture -
mozilla/DeepSpeech

There is one more README.md file present in the native_client directory
which stats about building the Tensorflow and DeepSpeech libraries.



> Try artifacts from TaskCluster on master branch, C++ client in
> native_client.tar.xz contains '-t' option and you can use the mmap
> trick. It should all be accessible from readme.

I am not getting your point from the above statement. slash
Can you please elaborate more on it?

1. My system contains HDD.
2. Total RAM is 15688592 kB.
3. Loading the model takes 0.469 sec while loading the loanguage model
takes 2.297 sec slash
Loaded model in 0.469s. slash
Loading language model from files .../models/lm.binary
.../models/trie slash
Loaded language model in 2.297s.

Please find below the details on CPU.

1. vendor name slash
slash [centerstage slash localhost slash ~ slash ] slash $ cat /proc/cpuinfo slash | grep vendor slash |
uniq slash
vendor_id : GenuineIntel

2. model name slash
slash [centerstage slash localhost slash ~ slash ] slash $ cat /proc/cpuinfo slash | grep 'model
name' slash | uniq slash
model name : Intel® Xeon® CPU E5-2609 v3 1.90GHz

3. Architecture slash
slash [centerstage slash localhost slash ~ slash ] slash $ lscpu slash
Architecture: x86_64 slash
CPU op-mode(s): 32-bit, 64-bit slash
Byte Order: Little Endian slash
CPU(s): 12 slash
On-line CPU(s) list: 0-11 slash
Thread(s) per core: 1 slash
Core(s) per socket: 6 slash
Socket(s): 2 slash
NUMA node(s): 2 slash
Vendor ID: GenuineIntel slash
CPU family: 6 slash
Model: 63 slash
Model name: Intel® Xeon® CPU E5-2609 v3 1.90GHz slash
Stepping: 2 slash
CPU MHz: 1200.117 slash
BogoMIPS: 3808.33 slash
Virtualization: VT-x slash
L1d cache: 32K slash
L1i cache: 32K slash
L2 cache: 256K slash
L3 cache: 15360K slash
NUMA node0 CPU(s): 0-5 slash
NUMA node1 CPU(s): 6-11 slash
slash [centerstage slash localhost slash ~ slash ] slash $

4. frequency/speed of the processor slash
slash [centerstage slash localhost slash ~ slash ] slash $ lscpu slash | grep -i mhz slash
CPU MHz: 1200.117

5. Multiple processor slash
slash [centerstage slash localhost slash ~ slash ] slash $ cat /proc/cpuinfo slash | grep -i
'physical id' slash | uniq slash
physical id : 0 slash
physical id : 1

6. Number of cores slash
slash [centerstage slash localhost slash ~ slash ] slash $ cat /proc/cpuinfo slash | grep -i 'core
id' slash
core id : 0 slash
core id : 1 slash
core id : 2 slash
core id : 3 slash
core id : 4 slash
core id : 5 slash
core id : 0 slash
core id : 1 slash
core id : 2 slash
core id : 3 slash
core id : 4 slash
core id : 5

[Archived Post]

[JRMeyer]

>>> lissyx
[March 1, 2018, 10:16am]

Thanks for those details. HDD + your CPU, it might be slow, but I don't
have an overview of how much. To try with mmap, please download
native_client.tar.xz from
https://tools.taskcluster.net/index/artifacts/project.deepspeech.deepspeech.native_client.master/cpu
and convert_graphdef_memmapped_format from
https://tools.taskcluster.net/index/project.deepspeech.tensorflow.pip.r1.5/cpu

Following those steps:
https://github.com/mozilla/DeepSpeech/blob/master/README.md#making-a-mmap-able-model-for-inference
please produce output_graph.pbmm from output_graph.pb. Then, using
the deepspeech binary from native_client.tar.xz you can run
inference (use .pbmm instead of .pb), and add an extra -t argument
at the end.

In the end,

$ ./deepspeech …/models/output_graph.pbmm …/models/alphabet.txt …/

With multiple audio files in .../, it will load the model once, and
perform multiple inferences. We should then be able to know better.

[Archived Post]

[JRMeyer]

>>> lissyx
[March 1, 2018, 6:05pm]

Someone filed an issue for the lack of Python 2.7 unicode build similar
to yours. I've just merged the fix, it should be available as soon as
https://tools.taskcluster.net/groups/PrzjPY-ITSK6cn9x4yr3yg completes.
Python package can then be installed from
https://index.taskcluster.net/v1/task/project.deepspeech.deepspeech.native_client.master.cpu/artifacts/public/deepspeech-0.1.1-cp27-cp27m-manylinux1_x86_64.whl
or
https://index.taskcluster.net/v1/task/project.deepspeech.deepspeech.native_client.master.cpu/artifacts/public/deepspeech-0.1.1-cp27-cp27mu-manylinux1_x86_64.whl

This is not yet published to pypi registry (will be with v0.2.0 release)

[next page
→

[Archived Post]