For Reproducing your issue
Please fill out the following:
Corpus structure
What language is the corpus in? Korean
How many files/speakers? 35 speakers and 23661 files
Are you using lab files or TextGrid files for input? yes i use lib files
Desktop (please complete the following information):
OS: [Linux]
Version [Ubuntu 20.04]
Any other details about the setup (miniconda)
Log file
INFO Training model...
INFO Completed training in 4171.303298711777 seconds!
INFO Saved model to TextGrid
INFO Done! Everything took 4370.606 seconds
INFO Stopping the global MFA database server...
ERROR pg_ctl stdout: waiting for server to shut down............................................................... failed
ERROR pg_ctl stderr: pg_ctl: server does not shut down
HINT: The "-m fast" option immediately disconnects sessions rather than
waiting for session-initiated disconnection.
Exception ignored in atexit callback: <function stop_server at 0x7f87e5329e10>
Traceback (most recent call last):
File "/home/sungwoo/miniconda3/envs/aligner_new/lib/python3.10/site-packages/montreal_forced_aligner/command_line/utils.py", line 470, in stop_server
raise DatabaseError(
montreal_forced_aligner.exceptions.DatabaseError: DatabaseError:
I don't know why the MFA is over just after the model is trained
Debugging checklist
[o] Have you updated to latest MFA version? (2.2.10) [o] Have you tried rerunning the command with the
--clean
flag?General installation (Linux)
conda create -n aligner -c conda-forge montreal-forced-aligner
RUN
mfa train --clean raw_data lexicon.txt ./TextGrid --punctuation "#@$%^" --sample_frequency "22050" --low_frequency "0" high_frequency "8000"
All folders have read and write permissions
For Reproducing your issue Please fill out the following:
Desktop (please complete the following information):
Log file
pg_log_global.txt