Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Kaldi recipes that are supported #97

Open
adamchant opened this issue Apr 25, 2020 · 0 comments
Open

Kaldi recipes that are supported #97

adamchant opened this issue Apr 25, 2020 · 0 comments

Comments

@adamchant
Copy link

adamchant commented Apr 25, 2020

Hey guys, I'm kinda new to kaldi. I have implemented the basic tri phone stages for librispeech and also trained the dnn stage using steps/train_nnet.sh script on fmmlr features, but when i try to run the gui demo script, i get an error log as follows, after replacing the models directory.
./gui-demo.py:14: PyGIWarning: Gtk was imported without specifying a version first. Use gi.require_version('Gtk', '3.0') before import to ensure that the right version gets loaded.
from gi.repository import GObject, Gst, Gtk, Gdk
ERROR ([5.5.684~1-03ae8]:ExpectToken():io-funcs.cc:200) Failed to read token [started at file position 333231], expected

[ Stack-Trace: ]
/home/dev/asr_toolkits/kaldi/src/lib/libkaldi-base.so(kaldi::MessageLogger::LogMessage() const+0xb42) [0x7f71b02f26b2]
../src/libgstkaldinnet2onlinedecoder.so(kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&)+0x21) [0x7f71b26bbedb]
/home/dev/asr_toolkits/kaldi/src/lib/libkaldi-base.so(kaldi::ExpectToken(std::istream&, bool, char const*)+0x17f) [0x7f71b02f4315]
/home/dev/asr_toolkits/kaldi/src/lib/libkaldi-nnet2.so(kaldi::nnet2::Nnet::Read(std::istream&, bool)+0x3e) [0x7f71abd0bf24]
/home/dev/asr_toolkits/kaldi/src/lib/libkaldi-nnet2.so(kaldi::nnet2::AmNnet::Read(std::istream&, bool)+0x14) [0x7f71abd19752]
../src/libgstkaldinnet2onlinedecoder.so(+0x6866e) [0x7f71b26af66e]
/usr/lib/x86_64-linux-gnu/libgobject-2.0.so.0(g_object_setv+0x23e) [0x7f71d7333bae]
/usr/lib/x86_64-linux-gnu/libgobject-2.0.so.0(g_object_set_property+0x1e) [0x7f71d7334b3e]
/usr/lib/python2.7/dist-packages/gi/_gi.x86_64-linux-gnu.so(+0x168b2) [0x7f71d77ba8b2]
/usr/lib/python2.7/dist-packages/gi/_gi.x86_64-linux-gnu.so(+0x16cab) [0x7f71d77bacab]
python(PyEval_EvalFrameEx+0x54a) [0x55d5e5a5bbba]
python(PyEval_EvalFrameEx+0x52b6) [0x55d5e5a60926]
python(PyEval_EvalCodeEx+0x58a) [0x55d5e5a592aa]
python(+0x10df29) [0x55d5e5a74f29]
python(+0x12670e) [0x55d5e5a8d70e]
python(+0x12633a) [0x55d5e5a8d33a]
python(+0xe30ab) [0x55d5e5a4a0ab]
python(PyEval_EvalFrameEx+0x54b0) [0x55d5e5a60b20]
python(PyEval_EvalCodeEx+0x58a) [0x55d5e5a592aa]
python(PyEval_EvalCode+0x19) [0x55d5e5a58d19]
python(+0x12294f) [0x55d5e5a8994f]
python(PyRun_FileExFlags+0x82) [0x55d5e5a84be2]
python(PyRun_SimpleFileExFlags+0x18d) [0x55d5e5a8460d]
python(Py_Main+0x616) [0x55d5e5a33356]
/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xe7) [0x7f71d8fc2b97]
python(_start+0x2a) [0x55d5e5a32c4a]

LOG ([5.5.6841-03ae8]:ComputeDerivedVars():ivector-extractor.cc:183) Computing derived variables for iVector extractor
LOG ([5.5.684
1-03ae8]:ComputeDerivedVars():ivector-extractor.cc:204) Done.
ASSERTION_FAILED ([5.5.684~1-03ae8]:LeftContext():nnet-nnet.cc:43) Assertion failed: (!components_.empty())

[ Stack-Trace: ]
/home/dev/asr_toolkits/kaldi/src/lib/libkaldi-base.so(kaldi::MessageLogger::LogMessage() const+0xb42) [0x7f71b02f26b2]
/home/dev/asr_toolkits/kaldi/src/lib/libkaldi-base.so(kaldi::KaldiAssertFailure_(char const*, char const*, int, char const*)+0x6e) [0x7f71b02f33ae]
/home/dev/asr_toolkits/kaldi/src/lib/libkaldi-nnet2.so(kaldi::nnet2::Nnet::LeftContext() const+0x5d) [0x7f71abd099ad]
/home/dev/asr_toolkits/kaldi/src/lib/libkaldi-nnet2.so(kaldi::nnet2::DecodableNnet2Online::DecodableNnet2Online(kaldi::nnet2::AmNnet const&, kaldi::TransitionModel const&, kaldi::nnet2::DecodableNnet2OnlineOptions const&, kaldi::OnlineFeatureInterface*)+0x57) [0x7f71abdb96f1]
/home/dev/asr_toolkits/kaldi/src/lib/libkaldi-online2.so(kaldi::SingleUtteranceNnet2Decoder::SingleUtteranceNnet2Decoder(kaldi::OnlineNnet2DecodingConfig const&, kaldi::TransitionModel const&, kaldi::nnet2::AmNnet const&, fst::Fst<fst::ArcTpl<fst::TropicalWeightTpl > > const&, kaldi::OnlineFeatureInterface*)+0x6b) [0x7f71b1e07203]
../src/libgstkaldinnet2onlinedecoder.so(+0x6e4b0) [0x7f71b26b54b0]
../src/libgstkaldinnet2onlinedecoder.so(+0x6f91c) [0x7f71b26b691c]
/usr/lib/x86_64-linux-gnu/libgstreamer-1.0.so.0(+0xab269) [0x7f71cd802269]
/usr/lib/x86_64-linux-gnu/libglib-2.0.so.0(+0x74b40) [0x7f71d7079b40]
/usr/lib/x86_64-linux-gnu/libglib-2.0.so.0(+0x74175) [0x7f71d7079175]
/lib/x86_64-linux-gnu/libpthread.so.0(+0x76db) [0x7f71d8d896db]
/lib/x86_64-linux-gnu/libc.so.6(clone+0x3f) [0x7f71d90c288f]

Aborted (core dumped)
Kindly help me understand and debug this log (i am a beginer with kaldi as well), as im unable to understand whats going on or make sense of it....
I get this is not the ivector based dnn am, do i have to run the tdnn scripts in local/nnet3 folder, is there any way I can use the dnn model along with this tool kit...?
Thanks

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant