-
ubuntu 14.04.
use thi command(.setup.py install) to setup kaldi-pthon, I have set $KALDI_ROOT already
the errors are as follows:
/usr/include/python2.7/numpy/npy_1_7_deprecated_api.h:15:2: warning:…
-
Hey guys, I notice there‘s on-the-fly feats in `asr_datamodule.py`:
https://github.com/k2-fsa/icefall/blob/32de2766d591d2e1a77c06a40d2861fb1bbcd3ad/egs/wenetspeech/ASR/pruned_transducer_stateless2/as…
-
On a Rasberry Pi 4 I get this exception on training in the web interface:
```
TrainingFailedException: Command '['fstcompile', '--isymbols=/home/pi/.config/rhasspy/profiles/de/kaldi/model/data/lang/…
-
Hi all
I have an issue about memory leak when I run kaldi code on RTX 3090
Memory didn't free when all processs done (done decode kaldi).
No code modification with my experiment.
Demo source:…
-
Both librispeech and librispeech_100 recipe contain a symlink to utils directory from kaldi:
https://github.com/espnet/espnet/blob/master/egs2/librispeech/asr1/utils and https://github.com/espnet/e…
-
I was having this weird issue; on an RTX2080TI training uses ~11GB of GPU RAM (with my batch size). But then, I switched to a Quadro rtx8000, the exact same experiment now uses ~27GB of GPU RAM!
I l…
-
i notice that when given short duration utterances, the PLDA score will have smaller aboslute value. Should there be something like score normalization?
-
I am trying to figure out the effect of setting speaker model in kaldi recognizer:
`rec.SetSpkModel(spk_model)`
How does this help in asr?
Is it only used in normalizing cmvn, or is there mor…
-
Hi All,
I am using CNTK for Speech Recognition and currently I use Kaldi reader with NDL/MEL. As the usage of NDL is depreciated, I am planning to use python for ASR. I have few questions for the…
-
Recipes for recently added lookahead decoding fail because lookahead libraries are built in `/lib/fst` rather then `/lib`
adding
`export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$KALDI_ROOT/tools/open…