-
in case the last argument is variable name ,parse_opts might get stuck in infinite lop , for example "./steps/nnet2/train_pnorm.sh --cmd run.pl --lda-opts"
the problem is that "shift 2" command …
-
Hi - I am looking for an example notebook where I want to train an ASR on a dataset such as TIMIT using ESPnet2 library calls. The data preparation is required to be done separately in Python (not usi…
-
Wav2vec2 makes it possible for low resource languages to build high quality acoustic models using only unlabelled audio. Finetuning this with a couple of hours of labelled data gives you a pretty good…
-
I'm a Kaldi noob but interested in using your set up for English. I looked at your other project and the Kaldi discussion boards, and this model seems like a good fit
http://kaldi-asr.org/downloads/b…
-
Hi, all
Can the conformer-ctc **phone-based** ASR model be trained by a training graph with a lexicon, which has optional silence in it? So there will be some extra silence tokens in the text like …
-
https://www.stateoftheart.ai/?area=Sound&task=Speaker%20Diarization
ghost updated
5 years ago
-
For the new CHiME-6 track 2 egg: https://github.com/kaldi-asr/kaldi/tree/master/egs/chime6/s5b_track2
The bug prevents from going beyond stage 1.
The file name data/srilm/best_3gram.gz has to be c…
-
-
The docs
http://kaldi-asr.org/doc/graph_recipe_test.html#graph_lexicon
seem to be out of date, as pointed out by Remi Francis. E.g. it says "Notice that we allow words with empty phonetic representa…
-
To prepare for a full provenance chain, it's good to start adding easy-to-obtain prov and timing information to the DANE Results of the ASR worker and the download worker.
Next to the desired provena…
jblom updated
2 years ago