Franck-Dernoncourt/ASR_benchmark
Program to benchmark various speech recognition APIs
This tool helps you evaluate and compare different automated speech recognition (ASR) services by transcribing your audio files and calculating how accurately they perform. You provide audio recordings and their correct text transcripts, and it outputs a performance score (word error rate) for each ASR provider. It's designed for anyone who needs to choose the best ASR service for their specific audio data.
No commits in the last 6 months.
Use this if you need to objectively compare several speech-to-text APIs to determine which one performs best on your unique audio content.
Not ideal if you're looking for an off-the-shelf transcription service rather than a tool to benchmark existing services.
Stars
81
Forks
18
Language
Python
License
—
Category
Last pushed
Sep 06, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Franck-Dernoncourt/ASR_benchmark"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
Uberi/speech_recognition
Speech recognition module for Python, supporting several engines and APIs, online and offline.
cmusphinx/pocketsphinx
A small speech recognizer
tensorflow/lingvo
Lingvo
modelscope/FunASR
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models,...
PyThaiNLP/pythaiasr
Python Thai Automatic Speech Recognition