jaesunghuh / simplediarization Goto Github PK
View Code? Open in Web Editor NEWSimple Diarization model
License: MIT License
Simple Diarization model
License: MIT License
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 day๐
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:
โ /home/emoman/.local/lib/python3.11/site-packages/sklearn/utils/validation.py:915 in check_array โ
โ โ
โ 912 โ โ โ โ "Convert your data to numeric values explicitly instead." โ
โ 913 โ โ โ ) โ
โ 914 โ โ if not allow_nd and array.ndim >= 3: โ
โ โฑ 915 โ โ โ raise ValueError( โ
โ 916 โ โ โ โ "Found array with dim %d. %s expected <= 2." โ
โ 917 โ โ โ โ % (array.ndim, estimator_name) โ
โ 918 โ โ โ ) โ
โฐโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโฏ
ValueError: Found array with dim 3. AgglomerativeClustering expected <= 2.
Any ideas?
Best,
Ed
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.