istupakov/onnx-asr
A lightweight Python package for Automatic Speech Recognition using ONNX models
This tool helps you convert spoken audio into written text quickly and efficiently. You provide audio files, typically in WAV format, and it outputs the corresponding transcription. It's ideal for anyone needing to process audio recordings into text, such as researchers analyzing interviews, content creators transcribing podcasts, or businesses automating call center transcriptions.
281 stars. Available on PyPI.
Use this if you need fast, accurate speech-to-text transcription for various audio files on a range of devices, from edge devices to powerful servers.
Not ideal if you require the absolute latest, bleeding-edge research models that are not yet converted to ONNX format or if you need an all-in-one solution that includes complex natural language processing beyond basic transcription.
Stars
281
Forks
27
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/istupakov/onnx-asr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Related tools
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