jaesunghuh / simplediarization Goto Github PK

I need to apply it to the code now. Do you have any encapsulated methods that can be directly called? If so, I haven't found any relevant documents, please give me some tips.

Hello, as a student interested in the field of speech, first of all, thank you for your wonderful research.
I was also surprised by the very good diarization performance for arbitrary data on YouTube.

After using it with interest, I have a question as below and leave it on the issue.

• Diarization was not successful for audio files whose sample rate is not 16000.
  Is it because most of the audio files used for the learning dataset have a sample rate of 16000?
  (I compared the same audio file with different sample rates)

• I wonder if you have any further research plans on diarization in the section where the utterances overlap.

Thank you for your wonderful research. Have a good day😊

Hello,

I have a file with three speakers:

yt-dlp -f bestaudio --extract-audio --audio-format wav --postprocessor-args "-ar 16000" --audio-quality 0 "https://www.youtube.com/watch?v=qHrN5Mf5sgo"

I believe that makes the clustering fail:

│ /home/emoman/.local/lib/python3.11/site-packages/sklearn/utils/validation.py:915 in check_array  │
│                                                                                                  │
│    912 │   │   │   │   "Convert your data to numeric values explicitly instead."                 │
│    913 │   │   │   )                                                                             │
│    914 │   │   if not allow_nd and array.ndim >= 3:                                              │
│ ❱  915 │   │   │   raise ValueError(                                                             │
│    916 │   │   │   │   "Found array with dim %d. %s expected <= 2."                              │
│    917 │   │   │   │   % (array.ndim, estimator_name)                                            │
│    918 │   │   │   )                                                                             │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
ValueError: Found array with dim 3. AgglomerativeClustering expected <= 2.

Any ideas?

Best,

Ed