search

prosodylab / Prosodylab-Aligner

Python interface for forced audio alignment using HTK and SoX
http://prosodylab.org/tools/aligner/
MIT License
331 stars 77 forks source link

Error: No paths found (do you plenty of training data?). #16

Closed jamiebullock closed 10 years ago

jamiebullock commented 10 years ago

Hi again, I have now got past the "Aligning..." step with my data, however it fails at making the TextGrids with the above error message.

Any ideas?

My speech data is multi-speaker, so maybe this is related to #3 ?

I will try splitting the audio file / text up and see if that improves the situation.

jamiebullock commented 10 years ago

Yup, I have this working now, at least with the first few examples I tried.

Looks like I'm going to have to pre-segment the audio using speaker identification! Closing the issue.