revdotcom/fstalign

An efficient OpenFST-based tool for calculating WER and aligning two transcript sequences.

42
/ 100
Emerging

Built on OpenFST finite-state composition with lazy traversal algorithms, it aligns reference and hypothesis token sequences while supporting both NLP-formatted and CTM input formats for detailed error analysis. Version 2.0 introduces optimized graph traversal that dramatically accelerates alignment on lengthy or error-rich sequences, plus intelligent constraint handling that prevents punctuation-word misalignments and favors case-insensitive substitutions. Provides configurable beam search, strict punctuation enforcement, and JSON output for integration into speech recognition evaluation pipelines.

171 stars.

No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 10 / 25

How are scores calculated?

Stars

171

Forks

11

Language

C++

License

Apache-2.0

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/revdotcom/fstalign"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.