jiwer
Evaluate your speech-to-text system with similarity measures such as word error rate (WER)
Installation
To install this package, run one of the following:
Usage Tracking
3.0.4
1 / 8 versions selected
Downloads (Last 6 months): 0
Description
JiWER is a simple and fast python package to evaluate an automatic speech recognition system. It supports the following measures: * word error rate (WER) * match error rate (MER) * word information lost (WIL) * word information preserved (WIP) * character error rate (CER)
About
Summary
Evaluate your speech-to-text system with similarity measures such as word error rate (WER)
Last Updated
Jun 6, 2025 at 12:27
License
Apache-2.0
Total Downloads
266
Supported Platforms
linux-64
linux-aarch64
macOS-arm64
win-64
macOS-64
GitHub Repository
https://github.com/jitsi/jiwerDocumentation
https://jitsi.github.io/jiwer