pocketsphinx

pocketsphinx copied to clipboard

Error while decoding pocketsphinx

1

When I train my model with 171 audios, I get a decoding error I'm using ubuntu 20.04 INFO: feat.c(713): Initializing feature stream to type: '1s_c_d_dd', ceplen=13, CMN='batch', VARNORM='no', AGC='none' ERROR:...

SarahKaren

I tried adapting a model with my own phonetic dictionary and language model. But now it gives me a problem that the sentences are not making but giving me one...

Gourav0407

[FEATURE REQUEST] Adding support for C# .NetCore on RaspberryPI?

1

I tried generating a wrapper for NetCore C# for Raspberry PI using the SWIG example, but after endless hours of trying, I just can't figure out how to make it...

dev-bre

OpenSUSE 15.1 wheel problem

2

Can't install on opensuse leap 15.1, is it possible? Please help.

SiddharthChabukswar

Recognized words differed of recognized phonemes. Recognizing the words gives this output pocketsphinx\bin\Release\x64>pocketsphinx_continuous.exe -infile "C:\1timkarlo\ai_short16000.wav" -hmm model\en-us\en-us -lm model\en-us\en-us.lm.bin -dict model\en-us\cmudict-en-us.dict -logfn nul the question of how real is artificial...

timkarlo

ERROR: "ngram_search.c", line 1207: Failed to find DAG node corresponding to </s>

1

I am getting a sentence error of 3.9% and word error rate of 4.0% with this error. what should I do? Is this error rate good already? or is it...

sudopsi4

Let user provide cross-built gstreamer

1

Hello, As reported on https://bugs.debian.org/955155 , while pocketsphinx currently disables gst support when cross-building, a `--with` option could be used to let the user provide the cross-built gstreamer: “ It...

sthibaul

LISTENING & RECOGNIZING function takes more time to execute

1

while running sphinx code it is taking more time to execute the LISTENING RECOGNIZING functions. The question is there any way to reduce the time consumption that these function takes?like...

srigandeswaran

segmentation fault after n x 4096 bytes written to a text file

1

I'm trying to run this command pocketsphinx_continuous -hmm /home/richard/test/PSAudio/en-us-adapt -lm /home/richard/test/PSAudio/en-us.lm.bin -dict /home/richard/test/PSAudio/newmerge01.dict -infile ./1001.wav > ./result1001.txt and I get a segmentation fault. The file ./1001.wav is ~ 191Mbytes I've...

richardalo

get_lattice().write() does not include probabilities

1

I'm looking to get possible guesses for words other then those appearing in the segment list. These look to be contained in the lattice. However, I don't see how those...

wiffleball28