Python module for evaluating speaker diarization.
Project description
Getting Started
This project is Speechmatics' fork of https://github.com/pyannote/pyannote-metrics used to calculate various speaker diarization metrics from reference/hypothesis transcript pairs.
To install the package:
pip install speechmatics-diarization-metrics
This package has a CLI supporting ctm, lab, or V2 JSON format transcripts and can be run using:
python3 -m sm_diarization_metrics.cookbook reference.json transcript.json
For further guidance run:
python3 -m sm_diarization_metrics.cookbook -h
Run from source code
If you would prefer to clone the repo and run the source code:
git clone git@github.com:speechmatics/speechmatics-python.git
cd speechmatics-python/metrics/sm_diarization_metrics
pip install -r ./requirements.txt
python3 -m sm_diarization_metrics.cookbook reference.json transcript.json
Build wheel
To build and install the wheel run:
make wheel
make install
Docs
Further description of how to use the tool and the metrics available are in sm_diarization_metrics.pdf
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 Distributions
Built Distribution
File details
Details for the file speechmatics_diarization_metrics-0.0.2-py3-none-any.whl
.
File metadata
- Download URL: speechmatics_diarization_metrics-0.0.2-py3-none-any.whl
- Upload date:
- Size: 65.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.8.15
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 84ccba52f06e0105b5118b2b23a99e791810fd09e810fc1ef1056536389e0bc0 |
|
MD5 | 56329b88634ea1fd4c5638fb1d9be694 |
|
BLAKE2b-256 | 9aa53e01500412729fe545dc3e154678296094f460e64f34f73862940379da34 |