ERROR [+2011] PutVFloor: cannot create vFloors
FATAL ERROR - Terminating program /raid2/home/amohan/HTK-3.4/bin/HCompV
Monday, July 25, 2011
HCompV Error +6313
ERROR [+6313] OpenParmChannel: EXF segment bigger than file
ERROR [+6313] OpenAsChannel: OpenParmChannel failed
ERROR [+6316] OpenBuffer: OpenAsChannel failed
ERROR [+2050] LoadFile: Config parameters invalid
FATAL ERROR - Terminating program /raid2/home/amohan/HTK-3.4/bin/HCompV
I am aware that this usually happens when the SCP files have segment or frame numbers that are larger than the specified parameter file, question though is: How does one track down which SCP file caused the problem? Would any options with trace parameters be useful?
ERROR [+6313] OpenAsChannel: OpenParmChannel failed
ERROR [+6316] OpenBuffer: OpenAsChannel failed
ERROR [+2050] LoadFile: Config parameters invalid
FATAL ERROR - Terminating program /raid2/home/amohan/HTK-3.4/bin/HCompV
I am aware that this usually happens when the SCP files have segment or frame numbers that are larger than the specified parameter file, question though is: How does one track down which SCP file caused the problem? Would any options with trace parameters be useful?
Thursday, July 21, 2011
Useful resources
1. To get HTK data structures into MATLAB it might be useful to use the mmf2matlab routine available from the toolbox here: http://www.bas.uni-muenchen.de/Bas/SV/ certain other useful routines might also be available.
2. A useful toolkit STK (http://speech.fit.vutbr.cz/software/hmm-toolkit-stk) is available from the Speech Processing Group from BUT, the description is as given below:
HMM Toolkit STK
HMM Toolkit STK from Speech@FIT
Authors:
Lukáš Burget, Ondřej Glembek, Petr Schwarz, Martin Karafiát
Overview:
A set of tools for training and recognition of HMM's. Probably the most interesting in this distribution is SERest - a tool for embedded training of HMM's with supporting scripts. Key features of SERest include re-estimation of linear transformations (MLLT, LDA, HLDA) within the training process, and use of recognition networks for the training.
Distributions:
The current version number is 2006_12_18
Binary distribution for Linux (I386), including some supporting scripts is available in stk_bin_linux-i386_2006_12_18.tgz
Source distribution is available in stk_src_2006_12_18.tgz
Examples:
2. A useful toolkit STK (http://speech.fit.vutbr.cz/software/hmm-toolkit-stk) is available from the Speech Processing Group from BUT, the description is as given below:
HMM Toolkit STK
HMM Toolkit STK from Speech@FIT
Authors:
Lukáš Burget, Ondřej Glembek, Petr Schwarz, Martin Karafiát
Overview:
A set of tools for training and recognition of HMM's. Probably the most interesting in this distribution is SERest - a tool for embedded training of HMM's with supporting scripts. Key features of SERest include re-estimation of linear transformations (MLLT, LDA, HLDA) within the training process, and use of recognition networks for the training.
Distributions:
The current version number is 2006_12_18
Binary distribution for Linux (I386), including some supporting scripts is available in stk_bin_linux-i386_2006_12_18.tgz
Source distribution is available in stk_src_2006_12_18.tgz
Examples:
Tuesday, July 19, 2011
Subscribe to:
Posts (Atom)