S
simedw
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: Ear - Mandarin Pronunciation
Comments URL: Show HN: I trained a 9M speech model to fix my Mandarin tones | Hacker News
Points: 150
# Comments: 49
Continue reading...
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: Ear - Mandarin Pronunciation
Comments URL: Show HN: I trained a 9M speech model to fix my Mandarin tones | Hacker News
Points: 150
# Comments: 49
Continue reading...