Error while decoding pocketsphinx
Opened this issue · 1 comments
When I train my model with 171 audios, I get a decoding error
I'm using ubuntu 20.04
INFO: feat.c(713): Initializing feature stream to type: '1s_c_d_dd', ceplen=13, CMN='batch', VARNORM='no', AGC='none'
ERROR: "acmod.c", line 78: Folder '/mnt/e/fin/asr/data/dyu/model_parameters/maisonconnectee_db_all.cd_cont_200' does not contain acoustic model definition 'mdef'
FATAL: "batch.c", line 913: PocketSphinx decoder init failed
Wed Jan 13 07:26:53 2021
Hi, this error message can unfortunately be misleading. If you still have access to this project, please do look and see if the file /mnt/e/fin/asr/data/dyu/model_parameters/maisonconnectee_db_all.cd_cont_200/mdef exists. But it could be that something else is wrong in the SphinxTrain configuration.