Hi, I'm using pocketsphinx version 0.7 to transcribe videos. When processing
some short audios less than 1 min, everything works well and the transcription
is very good. However, when I change to transcribe some long audios maybe
longer than 3min, following error will occur:
ERROR: "acmod.c", line 862: Circular feature buffer cannot be rewound (output frame 0, alloc -25938)
int16 frame; /**< Frame in which this HMM was last active; <0 if inactive */
to
int32 frame; /**< Frame in which this HMM was last active; <0 if inactive */
However, the program still could not work.
Besides, I also try to use sphinx_cont_fileseg to segment the long audio
files. This doesn't work neither.
So, I'd like to know how to handle long audio files with pocketsphinx? Thanks
in advance.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi, I'm using pocketsphinx version 0.7 to transcribe videos. When processing
some short audios less than 1 min, everything works well and the transcription
is very good. However, when I change to transcribe some long audios maybe
longer than 3min, following error will occur:
I've read a topic in this forum:
https://sourceforge.net/projects/cmusphinx/forums/forum/5471/topic/4556719
It seems we need to change the maximum value for frame num. So I changed the
defination of frame in hmm.h
from
to
However, the program still could not work.
Besides, I also try to use sphinx_cont_fileseg to segment the long audio
files. This doesn't work neither.
So, I'd like to know how to handle long audio files with pocketsphinx? Thanks
in advance.