julius
julius copied to clipboard
julius-speech
Open-Source Large Vocabulary Continuous Speech Recognition Engine
julius compiles fine, but when I try to execute the example from the README > ../julius/julius -C julius.jconf -dnnconf dnn.jconf it segfaults: > \### Recognition: 2nd pass (RL heuristic best-first)...
I have all commits up to July 1, "fixed charconv fails in mkbingram". When I run mkdfa.pl on my grammar and voca files I get this confusing output: ``` toki.grammar...
### input `../julius/julius/julius -C julius.jconf -dnnconf dnn.jconf ` ### output ``` ENVR-v5.3.am ENVR-v5.3.lm ENVR-v5.3.dct ENVR-v5.3.mfc ENVR-v5.3.layer2_bias.npy ENVR-v5.3.norm ENVR-v5.3.layer2_weight.npy ENVR-v5.3.phn ENVR-v5.3.layer3_bias.npy ENVR-v5.3.prior ENVR-v5.3.layer3_weight.npy README.md ENVR-v5.3.layer4_bias.npy dnn.jconf ENVR-v5.3.layer4_weight.npy julius-dnn-output.txt ENVR-v5.3.layer5_bias.npy julius-dnn.exe ENVR-v5.3.layer5_weight.npy...
A pull request has been merged that adds a new feature "**grammar search on the 1st pass**". To use it, get the latest code on master branch. It enables applying...
### Running own acoustic model + dictionary with given ENVR-v5.3 language models. Everything were fine before building HMM lexicon tree. Got cmd line error message: "wchmm_add_word: CDSET phoneme exist in...
Hello. Is there a way to run julius with an option, which actually would make it print just best sentence as an output? I run julius with that command: "julius...
I'm trying speech recognition using an automaton, but silent phonemes (SP) are never recognized. SP phonemes appear in the first path, but not in the second path. I tried with...
I want to use "Julius Japanese Dictation-kit" in my Java website to recognition user voice (real time). But, I don't know how to do it. I'm trying to use input...
I notice function 'wordgraph_compaction_thesame_sub' has a bug. 1. before delete we(wordgraph), we's leftwords and rightwords will be added to wg, except for each of them is equal wg. that's to...
Just installed following the instructions. I get to point 4. test mozilla.wav. I see lots of "WARNING: 00 _default: no tail silence word survived on the last frame, search failed"...
Metadata
Owner
Metadata
Open-Source Large Vocabulary Continuous Speech Recognition Engine