fgnt/meeteval
MeetEval - A meeting transcription evaluation toolkit
Implements specialized Word Error Rate metrics for multi-speaker meeting transcription including concatenated minimum-Permutation WER (cpWER), Optimal Reference Combination WER (ORC WER), and time-constrained variants that handle speaker diarization and temporal alignment. Supports multiple input formats (STM, CTM, SegLST, RTTM) with bidirectional conversion via `meeteval-io`, and provides interactive alignment visualization for error analysis across different WER definitions.
149 stars and 5,213 monthly downloads. Used by 1 other package. Available on PyPI.
Stars
149
Forks
18
Language
Python
License
MIT
Category
Last pushed
Jan 27, 2026
Monthly downloads
5,213
Commits (30d)
0
Dependencies
7
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/fgnt/meeteval"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
readbeyond/aeneas
aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka...
analyticsinmotion/werpy
🐍📦 Ultra-fast Python package for calculating and analyzing the Word Error Rate (WER). Built for...
kahne/fastwer
A PyPI package for fast word/character error rate (WER/CER) calculation
tabahi/bournemouth-forced-aligner
Extract phoneme-level timestamps from speeh audio.
wq2012/SimpleDER
A lightweight library to compute Diarization Error Rate (DER).