Git Product home page Git Product logo

Comments (13)

alumae avatar alumae commented on July 19, 2024

This usually happens when the plugin is not found. You can set the path by something like:

export GST_PLUGIN_PATH=~/tools/gst-kaldi-nnet2-online/src

from kaldi-gstreamer-server.

alumae avatar alumae commented on July 19, 2024

P.S. post-processor and full-post-processor properties can be used with nnet2 models.

from kaldi-gstreamer-server.

 avatar commented on July 19, 2024

Thank your for your answer!

I already set KALDI_ROOT et GST_PLUGIN_PATH and gst-inspect-1.0 kaldinnet2onlinedecoder printed me the properties properly. I tried different approaches to set manually is-live to TRUE but it didn't work.

For 'post-processor' and 'full-processor' (logging also), the properties aren't found nor when looking at the list properties for kaldinnet2onlinedecode..

I used sample_english_nnet2.yaml with modified parameters by the way!

from kaldi-gstreamer-server.

alumae avatar alumae commented on July 19, 2024

Can you post your yaml file?

from kaldi-gstreamer-server.

 avatar commented on July 19, 2024

Sure, here it is (in plain text file I couldn't post a yaml file?) : sample_librispeech.txt. I only changed the models and values from sample_english_nnet2.yaml

The commented lines gave me AttributeError

from kaldi-gstreamer-server.

alumae avatar alumae commented on July 19, 2024

Can you post the file that causes the problem, without commenting out lines? There are many commented lines in the file you gave.

from kaldi-gstreamer-server.

alumae avatar alumae commented on July 19, 2024

BTW, post-processor and full-post-processor are not properties of the decoder, but rather global properties. The corresponding lines should not be intented, just like in the original sample_english_nnet2.yaml. But it's hard to tell from your commented file is this what you did.

from kaldi-gstreamer-server.

 avatar commented on July 19, 2024

The only file I modified is sample_english_nnet2.yaml. Each commented line gave me an TypeError (and not an AttributeError sorry), basically :

TypeError: object of type Gstkaldinnet2onlinedecoder' does not have property 'x'

If I comment them I end up with the error I mentioned in my first post.
All the errors are from kaldigstserver/decoder2.py, line 62 for the first error mentioned and line 59 for the others!

from kaldi-gstreamer-server.

alumae avatar alumae commented on July 19, 2024

I need to see the exact file that causes you the problem.

from kaldi-gstreamer-server.

 avatar commented on July 19, 2024

Hi,

I sent you an email.

I've redone all the install (kaldi, gst-kaldi-nnet2-online and kaldi-gstreamer-server), checked the packages dependencies and launched the command line (without modifications of any files) :

python kaldigstserver/worker.py -u ws://localhost:8888/worker/ws/speech -c sample_english_nnet2.yaml

I end up with the same error I described in my first post. The master is okay, kaldinnet2onlinedecoder is found but the worker doesn't start.

from kaldi-gstreamer-server.

alumae avatar alumae commented on July 19, 2024

Turned out it was caused by the 'appsrc' GStreamer element not being found. Probably caused by broken install of GStreamer or something similar.

from kaldi-gstreamer-server.

HoneywellDemo0623 avatar HoneywellDemo0623 commented on July 19, 2024

I run into a similar problem with running Kaldi "worker". Here is the error message:

AttributeError: 'NoneType' object has no attribute 'set_property'

===================================================
sudo python kaldigstserver/worker.py -u ws://localhost:8888/worker/ws/speech -c sample_worker.yaml
DEBUG 2019-01-22 08:35:06,207 Starting up worker
2019-01-22 08:35:06 - INFO: decoder: Creating decoder using conf: {'timeout-decoder': 10, 'post-processor': "perl -npe 'BEGIN {use IO::Handle; STDOUT->autoflush(1);} s/(.*)/\1./;'", 'logging': {'version': 1, 'root': {'level': 'DEBUG', 'handlers': ['console']}, 'formatters': {'simpleFormater': {'datefmt': '%Y-%m-%d %H:%M:%S', 'format': '%(asctime)s - %(levelname)7s: %(name)10s: %(message)s'}}, 'disable_existing_loggers': False, 'handlers': {'console': {'formatter': 'simpleFormater', 'class': 'logging.StreamHandler', 'level': 'DEBUG'}}}, 'decoder': {'word-syms': 'test/models/english/voxforge/tri2b_mmi_b0.05/words.txt', 'model': 'test/models/english/voxforge/tri2b_mmi_b0.05/final.mdl', 'lda-mat': 'test/models/english/voxforge/tri2b_mmi_b0.05/final.mat', 'fst': 'test/models/english/voxforge/tri2b_mmi_b0.05/HCLG.fst', 'silence-phones': '1:2:3:4:5'}, 'silence-timeout': 60, 'out-dir': 'tmp', 'use-vad': False}
2019-01-22 08:35:06 - INFO: decoder: Setting decoder property: word-syms = test/models/english/voxforge/tri2b_mmi_b0.05/words.txt
Traceback (most recent call last):
File "kaldigstserver/worker.py", line 419, in
main()
File "kaldigstserver/worker.py", line 411, in main
decoder_pipeline = DecoderPipeline(conf)
File "/home/haudio/ai/tools/kaldi/tools/kaldi-gstreamer-server/kaldigstserver/decoder.py", line 25, in init
self.create_pipeline(conf)
File "/home/haudio/ai/tools/kaldi/tools/kaldi-gstreamer-server/kaldigstserver/decoder.py", line 55, in create_pipeline
self.asr.set_property(key, val)
AttributeError: 'NoneType' object has no attribute 'set_property'

from kaldi-gstreamer-server.

gilamsalem avatar gilamsalem commented on July 19, 2024

@HoneywellDemo0623
The issue is that the decoder failed to load the gstreamer plugin onlinegmmdecodefaster.
If you compiled it successfully, you should be able to run (from ~/kaldi/src/gst-plugin):
gst-inspect-1.0 onlinegmmdecodefaster
If the command run successfully, check that you set GST_PLUGIN_PATH env to the right path.
You can check it with running:
GST_PLUGIN_PATH=~/kaldi/src/gst-plugin gst-inspect-1.0 onlinegmmdecodefaster
(set kaldi root directory to the right path)

from kaldi-gstreamer-server.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.