search

opensource-spraakherkenning-nl / Kaldi_NL

Code related to the Dutch instance and user groups of the KALDI speech recognition toolkit
http://www.opensource-spraakherkenning.nl
Apache License 2.0
64 stars 16 forks source link

change file_types setting in decode.sh #3

Closed wmelder closed 7 years ago

wmelder commented 7 years ago

The Linux distribution I use (RHEL7) doesn't seem to have a proper mp3-plugin for sox available. So, during installation I ignored the warning and continued. Now, in de the decode.sh script the setting is as follows: file_types="wav mp3" # file types to include for transcription Can I safely edit this file and change the value to "wav"? Or will trouble come when some mp3 file is put in the input folder later?

wmelder commented 7 years ago

So this is what happens when mp3 file is put in input directory: Split 1 source file into 0 segment
cat: /home/asr/OUT/intermediate/data/ALL/spk2utt: No such file or directory No speech found, exiting.

I guess I'll have to preprocess with another tool for mp3 to wav conversion. I will install ffmpeg