gilamsalem
commented
5 years ago My worker yaml file:
timeout-decoder : 10
use-nnet2: True
decoder:
# All the properties nested here correspond to the kaldinnet2onlinedecoder GStreamer plugin properties.
# Use gst-inspect-1.0 ./libgstkaldionline2.so kaldinnet2onlinedecoder to discover the available properties
use-threaded-decoder: true
model : $ROOT/kaldi/egs/aspire/s5/exp/tdnn_7b_chain_online/final.mdl
word-syms : $ROOT/kaldi/egs/aspire/s5/exp/tdnn_7b_chain_online/graph_pp/words.txt
fst : $ROOT/kaldi/egs/aspire/s5/exp/tdnn_7b_chain_online/graph_pp/HCLG.fst
mfcc-config : $ROOT/kaldi/egs/aspire/s5/exp/tdnn_7b_chain_online/conf/mfcc.conf
ivector-extraction-config : $ROOT/kaldi/egs/aspire/s5/exp/tdnn_7b_chain_online/conf/ivector_extractor.conf
min-active: 200
max-active: 7000
beam: 15.0
lattice-beam: 6.0
acoustic-scale: 1.0
do-endpointing : false
endpoint-silence-phones : "1:2:3:4:5:6:7:8:9:10"
traceback-period-in-secs: 0.25
chunk-length-in-secs: 0.25
num-nbest: 10
nnet-mode: 3
# --frames-per-chunk=20
# --extra-left-context-initial=0
# --online=true
# --frame-subsampling-factor=3
# --config=$ROOT/kaldi/egs/aspire/s5/exp/tdnn_7b_chain_online/conf/online.conf
out-dir: tmp
use-vad: False
silence-timeout: 10
# Just a sample post-processor that appends "." to the hypothesis
post-processor: perl -npe 'BEGIN {use IO::Handle; STDOUT->autoflush(1);} s/(.*)/\1./;'
logging:
version : 1
disable_existing_loggers: False
formatters:
simpleFormater:
format: '%(asctime)s - %(levelname)7s: %(name)10s: %(message)s'
datefmt: '%Y-%m-%d %H:%M:%S'
handlers:
console:
class: logging.StreamHandler
formatter: simpleFormater
level: DEBUG
root:
level: DEBUG
handlers: [console]
alumae
Kidist-Abraham
Hi,
I have an issue while running online decoding using websockets. My setup runs Aspire nnet3 model (http://kaldi-asr.org/models/m4). The issue is that master stop getting partial results from the worker after x responses (arbitrary number).
I tried to dig in the worker log and I saw that the worker itself processing all the partial and also the final result.
From the worker log it seems that a second post processing call is launched before the previous one ends (this is the exact point where the master stop to get messages).
What can be the problem?