[BUG] mfa transcribe completes successfully but the transcript has "<ukn>"

[stefanocoretta]

Debugging checklist

[x] Have you updated to latest MFA version?
[x] Have you tried rerunning the command with the --clean flag?

Describe the issue

When running mfa transcribe, the output .lab file contains a couple of <ukn> strings only.

For Reproducing your issue
Please fill out the following:

1. Corpus structure
   • What language is the corpus in? English
   • How many files/speakers? 1 file, 1 speaker
   • Are you using lab files or TextGrid files for input? NA
2. Dictionary
   • Are you using a dictionary from MFA? If so, which one? english_uk_mfa
   • If it's a custom dictionary, what is the phoneset? NA
3. Acoustic model
   • If you're using an acoustic model, is it one download through MFA? If so, which one? english_mfa
   • If it's a model you've trained, what data was it trained on? NA

Log file
Please attach the log file for the run that encountered an error (by default these will be stored in ~/Documents/MFA).

log.zip

Desktop (please complete the following information):

• OS: macOS
• Version: Sonoma 14.2.1 (23C71)
• Any other details about the setup (Cloud, Docker, etc): local conda installation

Additional context

The wav file I tried to transcribe has only one sentence (it's a test file).

[Mukity]

check the number of channels in your audio.
if they are 2 set the channels to 1

in python:

from pydub import AudioSegment
sound = AudioSegment.from_wav("/path/to/file.wav")
sound = sound.set_channels(1)
sound.export("/output/path.wav", format="wav")