gibberish_detector_onnx: quantized

# pip install 'optimum[onnxruntime,exporters]'
from optimum.pipelines import pipeline


classifier = pipeline(
    "text-classification",
    model="pszemraj/gibberish_detector_onnx-quant-avx512_vnni",
    accelerator="ort",
)
classifier("ayy waddup")
# [{'label': 'noise', 'score': 0.5396928787231445}]

Note: If you use this on a machine that doesn't have avx512_vnni (run lscpu | grep avx512_vnni), your output may differ from the one in the comment.