fgnt/meeteval

MeetEval - A meeting transcription evaluation toolkit

63
/ 100
Established

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.

Maintenance 10 / 25
Adoption 20 / 25
Maturity 18 / 25
Community 15 / 25

How are scores calculated?

Stars

149

Forks

18

Language

Python

License

MIT

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.