belambert/asr-evaluation
Python module for evaluating ASR hypotheses (e.g. word error rate, word recognition rate).
This tool helps researchers and developers working with Automatic Speech Recognition (ASR) systems assess their performance. You provide two text files: one with the correct, reference transcription and another with the ASR system's predicted transcription. It then calculates standard metrics like Word Error Rate (WER), Word Recognition Rate, and Sentence Error Rate, which are crucial for evaluating how accurately an ASR system transcribes audio.
283 stars. No commits in the last 6 months.
Use this if you need to objectively measure and compare the accuracy of different Automatic Speech Recognition models or transcripts.
Not ideal if you need to evaluate ASR systems based on factors beyond text accuracy, such as latency or speaker diarization.
Stars
283
Forks
78
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 15, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/belambert/asr-evaluation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
kahne/fastwer
A PyPI package for fast word/character error rate (WER/CER) calculation
analyticsinmotion/werpy
🐍📦 Ultra-fast Python package for calculating and analyzing the Word Error Rate (WER). Built for...
fgnt/meeteval
MeetEval - A meeting transcription evaluation toolkit
tabahi/bournemouth-forced-aligner
Extract phoneme-level timestamps from speeh audio.
wq2012/SimpleDER
A lightweight library to compute Diarization Error Rate (DER).