I have installed julius according to the Quick Run instructions on their git repo, but am getting mixed results that never run. However, when running the Quickstart suggested in this thread I have been able to get the program running.
Using the command meant to recognize an audio file included with the "official" julius demo, ../julius/julius/julius -C mic.jconf -dnnconf dnn.jconf -input mic, I get the following errors:
STAT: include config: julius.jconf
Stat: para: parsing HTK Config file: wav_config
Warning: para: "SOURCEFORMAT" ignored (not supported, or irrelevant)
Warning: para: TARGETKIND skipped (will be determined by AM header)
Stat: para: TARGETRATE=100000.0
Warning: para: "SAVECOMPRESSED" ignored (not supported, or irrelevant)
Warning: para: "SAVEWITHCRC" ignored (not supported, or irrelevant)
Stat: para: WINDOWSIZE=250000.0
Stat: para: USEHAMMING=T
Stat: para: PREEMCOEF=0.97
Stat: para: NUMCHANS=26
Stat: para: CEPLIFTER=22
Warning: para: NUMCEPS skipped (will be determined by AM header)
Warning: no SOURCERATE found
Warning: assume source waveform sample rate to 625 (16kHz)
ERROR: m_options: wrong argument: "-dnnconf"
Try `-help' for more information.
The Quickstart runs on the mic using julius -input mic -C dnn.jconf, I have modified it to julius -input mozilla.wav -C dnn.jconf in the directory created for the julius demo, but get the error message Segmentation fault (core dumped).
It's clear that there is no problem receiving audio from the mic, but I am not sure where I'm going wrong on the julius-speech quick run. Any suggestions would be much appreciated!
The problem was my lack of understanding in how to modify the dnn.jconf file. As of 4.5 the dnn.jconf should read:
feature_type MFCC_E_D_A_Z
feature_options -htkconf wav_config -cvn -cmnload ENVR-v5.3.norm -cvnstatic
num_threads 1
feature_len 48
context_len 11
input_nodes 528
output_nodes 7461
hidden_nodes 1536
hidden_layers 5
W1 ENVR-v5.3.layer2_weight.npy
W2 ENVR-v5.3.layer3_weight.npy
W3 ENVR-v5.3.layer4_weight.npy
W4 ENVR-v5.3.layer5_weight.npy
W5 ENVR-v5.3.layer6_weight.npy
B1 ENVR-v5.3.layer2_bias.npy
B2 ENVR-v5.3.layer3_bias.npy
B3 ENVR-v5.3.layer4_bias.npy
B4 ENVR-v5.3.layer5_bias.npy
B5 ENVR-v5.3.layer6_bias.npy
output_W ENVR-v5.3.layerout_weight.npy
output_B ENVR-v5.3.layerout_bias.npy
state_prior_factor 1.0
state_prior ENVR-v5.3.prior
state_prior_log10nize false
Then it will work exactly as the Quickstart lays out. See this closed issue from the julius repo.