Skip to main content

A feature extraction extension for the pyannote framework

Project description

pyannote-shennong-features

A feature extractor for Pyannote that is based on the Shennong library

Installation

This library depends on Shennong, which is available on conda. Thus, make sure you're in a conda environment where pyannote-audio has been installed already and run

conda install -c coml shennong

Then you can pip-install the library in a regular way:

pip install pyannote.features.shennong

Pyannote Configuration

To use features from this library, this is the kind of configuration you should add your config.yml file:

feature_extraction:
   name: pyannote.features.ShennongMfcc
   params:
       coefs: 19
       e: True
       D: True
       DD: True
       mfccWindowType: 'hanning'
       mfccLowFreq: 20
       mfccHighFreq: -100 # Real value will be (f_nyquist - 100)
       with_pitch: True
       with_cmvn: False
       duration: 0.025
       step: 0.010
       sample_rate: 16000
       pitchFmin: 20
       pitchFmax: 500

Project details


Release history Release notifications | RSS feed

This version

0.1

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pyannote.features.shennong-0.1.tar.gz (7.2 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page