goodmike31/pl-asr-bigos-tools
Extendable toolkit for comprehensive evaluation of ASR systems. Currently supports benchmarking 29 system-models combination for Polish using BIGOS datasets.
Provides a standardized evaluation pipeline for diverse ASR engines (Google Cloud, Azure, Whisper, NeMo, MMS, Wav2Vec, OWSM) through a modular architecture supporting hypothesis generation, metric computation (WER, CER, MER), and result visualization. The framework uses Prefect workflows and JSON/INI configuration to orchestrate end-to-end evaluation across BIGOS and PELCRA datasets, with extensibility for custom ASR systems and datasets following the standardized BIGOS format.
Stars
11
Forks
2
Language
Python
License
MIT
Category
Last pushed
Mar 04, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/goodmike31/pl-asr-bigos-tools"
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
istupakov/onnx-asr
A lightweight Python package for Automatic Speech Recognition using ONNX models
PyThaiNLP/pythaiasr
Python Thai Automatic Speech Recognition
haoheliu/voicefixer
General Speech Restoration