Compiling the 0 4 1 client on windows

[JRMeyer]

>>> thegiffman
[April 16, 2019, 5:54pm]

Hi Everyone,

I'm building a VR experience for a trade show in July, and part of the
experience will involve a conversation with someone on a smart phone
(e.g. https://www.talktothereasons.com). I'd love to use DeepSpeech in
a conversation engine for this - listening to the mic and letting the
user say one of two choices. I think the current trained English model
would work just fine - I can use a fuzzy string comparison on the
predetermined answer and thus make the choice. I've already tested 0.4.1
on a Ubuntu VM and it performs well. But we'll need to get the client
built for Windows to move forward.

I'd be happy to use 0.5.0 as that already has a Windows client, but
unfortunately it looks like ya'll don't have a trained model ready yet.
So I'll need to do my best to compile 0.4.1 on Windows using Visual
Studio.

I'll be carefully following this
guide,
as well as the thread
here.
Hopefully it will be as simple as grabbing the solution from 0.5.0 and
compiling the 0.4.1 code with it, but I know better than to be so
optimistic.

This seems like a really friendly and helpful community of developers
here. I'll do my best to give a good faith effort, and I hope y'all
won't mind giving the odd tip if I run into trouble. Thanks in advance!

[This is an archived TTS discussion thread from discourse.mozilla.org/t/compiling-the-0-4-1-client-on-windows]

[JRMeyer]

>>> carlfm01
[April 16, 2019, 7:18pm]

,

You can start testing with my fork, I'm almost sure it was 0.4.1 on
master, and use branch r1.12 of Mozilla's Tensorflow.

TF : https://github.com/mozilla/tensorflow/tree/r1.12 slash
My fork with 0.4.1: https://github.com/carlfm01/DeepSpeech

It should work following the same guide you mentioned. Let me know if it
works.Any feedback well appreciated.



[How can I use the pre-trained model with alpha
versions?

[Archived Post]

[JRMeyer]

>>> carlfm01
[April 16, 2019, 7:22pm]

If you need just the client and not to compile and modify it you can
test with my old clients. slash

{.site-icon width='32'
GitHub

### carlfm01/deepspeech-tempwinbuilds

Contribute to carlfm01/deepspeech-tempwinbuilds development by creating
an account on GitHub.

If you need you use the .NET client with 0.4.1 please use it from

[Archived Post]

[JRMeyer]

>>> thegiffman
[April 16, 2019, 7:34pm]

Works great! Exactly what I need to save me days of work and
uncertainty.

Thanks a million. Can I buy you a drink or something?
![:wink:](

[Archived Post]

[JRMeyer]

>>> thegiffman
[April 17, 2019, 1:48pm]

,

A few questions on your client. It's actually great for me to use the
precompiled binary, as that really is all I need. But a few things
aren't as expected.

1. When I run 'DeepSpeechConsole.exe', the process hangs after the
output. It never terminates. This seems a bit unusual.
2. I do get a transcription back, but it's not the same one I get on
the linux version of 0.4.1 - it seems poorer quality. Any idea what
would cause that?

It may still be fine for my needs, but I thought I'd ask.

[Archived Post]

[JRMeyer]

>>> carlfm01
[April 17, 2019, 5:08pm]



> When I run 'DeepSpeechConsole.exe', the process hangs after the
> output. It never terminates. This seems a bit unusual.

Are you using the compiled .NET client? I'm afraid that you will need to
compile with the current master to avoid: slash

github.com/carlfm01/DeepSpeech

#### Remove unnecessary read key

{.message style='white-space: normal;'}<br/> The readkey is keeping DS process alive.<br/>

by carlfm01 on 07:09PM - 28 Feb 19
UTC

changed 1 files with 0 additions and 1 deletions.



> I do get a transcription back, but it's not the same one I get on the
> linux version of 0.4.1 - it seems poorer quality. Any idea what would
> cause that?

Using the same format? 16kHz, 16 bit depth and mono?

And yes, the Windows client is just a little worse, almost 1% worse.

Did the test here: slash

{.site-icon width='32'
GitHub

### carlfm01/DeepSpeech-Windows-WER

WER test for Mozilla slash 's Windows DeepSpeech client. Contribute to
carlfm01/DeepSpeech-Windows-WER development by creating an account on
GitHub.

[Archived Post]

[JRMeyer]

>>> thegiffman
[April 17, 2019, 6:23pm]

OK - that confirms my issues on both counts. Neither of them are
necessarily deal-breakers, though it's strange to see a quality drop. It
was the same wav file. I wonder why that is?

[Archived Post]

[JRMeyer]

>>> carlfm01
[April 17, 2019, 7:47pm]

Please check the BEAM_WIDTH is the same for both.

github.com

#### carlfm01/DeepSpeech/blob/35ebcd2075fc60fa9b783ab377b9f51092a29191/examples/net_framework/CSharpExamples/DeepSpeechConsole/Program.cs slash #L41

<br/> {<br/> model = GetArgument(args, '--model');<br/> alphabet = GetArgument(args, '--alphabet');<br/> lm = GetArgument(args, '--lm');<br/> trie = GetArgument(args, '--trie');<br/> audio = GetArgument(args, '--audio');<br/> }<br/> <br/> const uint N_CEP = 26;<br/> const uint N_CONTEXT = 9;<br/> const uint BEAM_WIDTH = 200;<br/> const float LM_ALPHA = 0.75f;<br/> const float LM_BETA = 1.85f;<br/> <br/> Stopwatch stopwatch = new Stopwatch();<br/> <br/> using (IDeepSpeech sttClient = new DeepSpeech())<br/> {<br/> var result = 1;<br/> Console.WriteLine('Loading model...');<br/> stopwatch.Start();<br/>

github.com

#### carlfm01/DeepSpeech/blob/35ebcd2075fc60fa9b783ab377b9f51092a29191/examples/vad_transcriber/wavTranscriber.py slash #L21

<br/> param alphabet: Alphabet.txt file<br/> param lm: Language model file<br/> param trie: Trie file<br/> <br/> Retval<br/> Returns a list [DeepSpeech Object, Model Load Time, LM Load Time]<br/> '''<br/> def load_model(models, alphabet, lm, trie):<br/> N_FEATURES = 26<br/> N_CONTEXT = 9<br/> BEAM_WIDTH = 500<br/> LM_ALPHA = 0.75<br/> LM_BETA = 1.85<br/> <br/> model_load_start = timer()<br/> ds = Model(models, N_FEATURES, N_CONTEXT, alphabet, BEAM_WIDTH)<br/> model_load_end = timer() - model_load_start<br/> logging.debug('Loaded model in %0.3fs.' % (model_load_end))<br/> <br/> lm_load_start = timer()<br/> ds.enableDecoderWithLM(alphabet, lm, trie, LM_ALPHA, LM_BETA)<br/>

[Archived Post]

[JRMeyer]

>>> carlfm01
[April 17, 2019, 7:50pm]

This an issue, also upstream is set to 200.

github.com

#### mozilla/DeepSpeech/blob/1e601d5c4aea0c7bc9f853f313593275945393e6/native_client/dotnet/DeepSpeechConsole/Program.cs slash #L41

<br/> {<br/> model = GetArgument(args, '--model');<br/> alphabet = GetArgument(args, '--alphabet');<br/> lm = GetArgument(args, '--lm');<br/> trie = GetArgument(args, '--trie');<br/> audio = GetArgument(args, '--audio');<br/> }<br/> <br/> const uint N_CEP = 26;<br/> const uint N_CONTEXT = 9;<br/> const uint BEAM_WIDTH = 200;<br/> const float LM_ALPHA = 0.75f;<br/> const float LM_BETA = 1.85f;<br/> <br/> Stopwatch stopwatch = new Stopwatch();<br/> <br/> using (IDeepSpeech sttClient = new DeepSpeech())<br/> {<br/> var result = 1;<br/> Console.WriteLine('Loading model...');<br/> stopwatch.Start();<br/>

[Archived Post]