A dependency-light Python script (standard library only) that takes paired objective metric scores and human MOS — optionally with per-clip MOS confidence intervals — and prints the full ITU-T P.1401-style validation report: Pearson PCC, Spearman SROCC, Kendall KROCC, RMSE, and the outlier ratio, with a monotonic mapping applied before the linear statistics (a built-in least-squares fit, or the 5-parameter logistic when SciPy is available). Reads a CSV or runs on a built-in sample dataset, expla
Download free PDF