revdotcom/fstalign
An efficient OpenFST-based tool for calculating WER and aligning two transcript sequences.
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.
Stars
171
Forks
11
Language
C++
License
Apache-2.0
Category
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.
Higher-rated alternatives
daanzu/kaldi-active-grammar
Python Kaldi speech recognition with grammars that can be set active/inactive dynamically at decode-time
gooofy/py-kaldi-asr
Some simple wrappers around kaldi-asr intended to make using kaldi's (online) decoders as...
nttcslab-sp/kaldiio
A pure python module for reading and writing kaldi ark files
pykaldi/pykaldi
A Python wrapper for Kaldi
kaldi-asr/kaldi
kaldi-asr/kaldi is the official location of the Kaldi project.