Saturday, 31 January 2026

New best story on Hacker News: Show HN: I trained a 9M speech model to fix my Mandarin tones

Show HN: I trained a 9M speech model to fix my Mandarin tones
442 by simedw | 133 comments on Hacker News.
Built this because tones are killing my spoken Mandarin and I can't reliably hear my own mistakes. It's a 9M Conformer-CTC model trained on ~300h (AISHELL + Primewords), quantized to INT8 (11 MB), runs 100% in-browser via ONNX Runtime Web. Grades per-syllable pronunciation + tones with Viterbi forced alignment. Try it here: https://ift.tt/tJyZ6aq