Issues 共 8
Why is audio segmented? Whats the purpose of it before it is sent to the E2E model?
#9 · Nishchalam · 2026-03-03
Can I Train My Own Model and How to Do It?
#8 · Bebra777228 · 2025-05-14
有关非人声部分
#7 · xingyuesama · 2024-08-07
Reproduce the paper on MIR_ST500 or MDB-stem-synth
#6 · hdnhan · 2024-06-17
cuDNN version? cuDNN 版本？
#5 · ZeaMays14142 · 2024-06-05
关于许可
#4 · CNChTu · 2024-01-11
Does the repository plan to have an open source license
#2 · yxlllc · 2023-07-07
很期待这个比crepe效果还好的模型
#1 · MaxMax2016 · 2023-06-30