Comments (13)
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.
P.S. post-processor and full-post-processor properties can be used with nnet2 models.
from kaldi-gstreamer-server.
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.
Can you post your yaml file?
from kaldi-gstreamer-server.
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.
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.
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.
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.
I need to see the exact file that causes you the problem.
from kaldi-gstreamer-server.
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.
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.
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.
@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)
- python kaldigstserver/client.py -r 32000 test/data/english_test.raw gives only THE. as output
- single word audio file gives multiple results, how to choose the correct result? HOT 1
- gstkaldinnet2onlinedecoder vs online2-tcp-nnet3-decoder-faster HOT 7
- The pretrained Chinese model can not process audio file with 48khz sample rate HOT 1
- Error switching between Audio types
- Error when running python kaldigstserver/worker.py on sample chinese HOT 1
- How to get phone alignment and word alignment information
- decoder with CSJ -> worker: segmentation fault (core dumped) HOT 2
- Enable Multiple channels listening HOT 1
- setting up the server for http api call HOT 2
- INTEL MKL ERROR: /opt/intel/mkl/lib/intel64/libmkl_avx2.so: undefined symbol: mkl_sparse_optimize_bsr_trsm_i8. Intel MKL FATAL ERROR: Cannot load libmkl_avx2.so or libmkl_def.so. HOT 2
- server can not get EOS HOT 1
- when I run it in doocker and use the chinese model ,it have this question :2021-04-16 05:52:17 - INFO: __main__: 7404beee-0d39-4d67-963c-01c58da10193: Waiting for EOS from decoder 2021-04-16 05:52:18 - INFO: __main__: 7404beee-0d39-4d67-963c-01c58da10193: Waiting for EOS from decoder HOT 2
- How to run multiple models in a single machine
- How can I save the incoming audio stream to wav file ?
- Invalid parameters supplied to OnlineLdaInput
- cannot download tedlium_nnet_ms_sp_online.tgz HOT 3
- worker process killed when worker replications reach to 3
- Poor performance with nnet3 TDNN-F model
- Any updates of year 2023???
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from kaldi-gstreamer-server.