Comments (3)
alumae
commented on August 19, 2024
-
Currently, the server sends out intermediate hypotheses every 0.5 seconds (changeable using the traceback-period-in-secs decoder parameter). I think it's a good idea not to send out non-final hypothesis if it hasn't changed, I'll look at it.
-
Yes, it breaks up speech based on silence, when the
do-endpointingdecoder parameter is set to True (see the sample_english_nnet2.yaml). There are many parameters that can be set to change how this endpointing is exactly done, check the endpoint* parameters of the decoder (I'm assuming you use the new DNN-based decoder). -
If you won't send EOS, decoder assumes that there is more audio coming and waits (until
silence-timeoutseconds pass, then the connection is closed by the server).
from kaldi-gstreamer-server.
mosherayman
commented on August 19, 2024
thanks
i dont see the endpoint* parameters in the decoder, which file should I look in?
from kaldi-gstreamer-server.
alumae
commented on August 19, 2024
If we use the Kaldi DNN-based decoder (https://github.com/alumae/gst-kaldi-nnet2-online), then
the properties specified in the configuration YAML file, nested under decoder, will be forwarded to the plugin. To see which properties are avialble, use gst-inspect-1.0 kaldinnet2onlinedecoder.
The properties that change the way endpointing is done are:
do-endpointing : If true, apply endpoint detection, and split the audio at endpoints
endpoint-silence-phones: List of phones that are considered to be silence phones by the endpointing code.
endpoint-rule1-must-contain-nonsilence: If true, for this endpointing rule to apply there mustbe nonsilence in the best-path traceback.
endpoint-rule1-min-trailing-silence: This endpointing rule requires duration of trailing silenceto be >= this value.
endpoint-rule1-max-relative-cost: This endpointing rule requires relative-cost of final-states to be <= this value (describes how good the probability of final-states is).
endpoint-rule1-min-utterance-length: This endpointing rule requires utterance-length (in seconds) to be >= this value.
endpoint-rule2-must-contain-nonsilence: If true, for this endpointing rule to apply there mustbe nonsilence in the best-path traceback.
endpoint-rule2-min-trailing-silence: This endpointing rule requires duration of trailing silenceto be >= this value.
endpoint-rule2-max-relative-cost: This endpointing rule requires relative-cost of final-states to be <= this value (describes how good the probability of final-states is).
endpoint-rule2-min-utterance-length: This endpointing rule requires utterance-length (in seconds) to be >= this value.
endpoint-rule3-must-contain-nonsilence: If true, for this endpointing rule to apply there mustbe nonsilence in the best-path traceback.
endpoint-rule3-min-trailing-silence: This endpointing rule requires duration of trailing silenceto be >= this value.
endpoint-rule3-max-relative-cost: This endpointing rule requires relative-cost of final-states to be <= this value (describes how good the probability of final-states is).
endpoint-rule3-min-utterance-length: This endpointing rule requires utterance-length (in seconds) to be >= this value.
endpoint-rule4-must-contain-nonsilence: If true, for this endpointing rule to apply there mustbe nonsilence in the best-path traceback.
endpoint-rule4-min-trailing-silence: This endpointing rule requires duration of trailing silenceto be >= this value.
endpoint-rule4-max-relative-cost: This endpointing rule requires relative-cost of final-states to be <= this value (describes how good the probability of final-states is).
endpoint-rule4-min-utterance-length: This endpointing rule requires utterance-length (in seconds) to be >= this value.
endpoint-rule5-must-contain-nonsilence: If true, for this endpointing rule to apply there mustbe nonsilence in the best-path traceback.
endpoint-rule5-min-trailing-silence: This endpointing rule requires duration of trailing silenceto be >= this value.
endpoint-rule5-max-relative-cost: This endpointing rule requires relative-cost of final-states to be <= this value (describes how good the probability of final-states is).
endpoint-rule5-min-utterance-length: This endpointing rule requires utterance-length (in seconds) to be >= this value.
You might have to dig into the Kaldi sources to understand what exactly different properties do. The defaults are however pretty good.
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.