X-MDD: LLM-Based Mispronunciation Detection and Diagnosis for Unseen Languages with Canonical References
Paper โข 2610.23079 โข Published
Main checkpoint of X-MDD: LLM-Based Mispronunciation Detection and Diagnosis for Unseen Languages with Canonical References (arXiv:2610.23079).
| File | Content |
|---|---|
model.safetensors |
Weights (bf16; keys asr.* = Qwen3-ASR; ctc_head.* = an unused CTC head, ignored at inference) |
config.yaml |
Inference config (prompt layout, language prefixes, model settings) |
processor/ |
Qwen3-ASR processor and tokenizer, including the added prompt boundary tokens |
phone_vocabulary.txt |
The 242-phone training vocabulary (zh tonal phones + CMU 39 phones), in index order |
arabic_phone_symbols.txt |
Phone symbols used for constrained decoding on Arabic (QuranMB) |
Install the X-MDD code, then follow the README.md there.
@article{wang2026xmdd,
title = {X-MDD: LLM-Based Mispronunciation Detection and Diagnosis for Unseen Languages with Canonical References},
author = {Wang, Xintong and Zhao, Junchuan and Wang, Ye},
journal = {arXiv preprint arXiv:2610.23079},
year = {2026}
}
Base model
Qwen/Qwen3-ASR-1.7B