revdotcom/fstalign

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

46
/ 100
Emerging

This tool helps speech-to-text transcriptionists and NLP engineers evaluate and refine automated speech recognition (ASR) outputs. It takes a correct reference transcript and a hypothesis transcript (the ASR output) to calculate the Word Error Rate (WER) and align the two sequences. This helps pinpoint exactly where the ASR system made errors (insertions, deletions, or substitutions) and understand the nature of those errors.

171 stars.

Use this if you need to accurately measure the performance of a speech-to-text system and understand specific alignment differences between human-generated and machine-generated transcripts.

Not ideal if you are looking for a general-purpose text comparison tool or a system that works with non-sequential or heavily structured data.

speech-to-text transcription-analysis ASR-evaluation natural-language-processing audio-transcription
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 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.