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
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Close
Hashes for pyannote.features.shennong-0.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 4a27837acb0af9baac5c93997d1543660c0fd7be98869979c42e64bb49005a18 |
|
MD5 | ca309f791e0efd98d946d7d922303113 |
|
BLAKE2b-256 | aa6d89cfa3d80edb410f553c73ad86743f03996ceb8f7c482ff73dd3211684d9 |