search

guxm2021 / SVT_SpeechBrain

[TOMM 2024] Automatic Lyric Transcription and Automatic Music Transcription from Multimodal Singing
Apache License 2.0
16 stars 4 forks source link

Can you give the .pt or .ckpt or something else, and the inference code? #1

Open Lindsay284 opened 2 weeks ago

Lindsay284 commented 2 weeks ago

Looking forward to your response, thank you!!!

guxm2021 commented 2 weeks ago

Please go to https://github.com/guxm2021/SVT_SpeechBrain/tree/main/MIR_ST500 to follow the code. You can put the provided models in the right directory and then you will skip the training. You can also prepare your data follow the same way as I process MIR-ST500 or other datasets. Afterwards, you can change test sets to your own datasets and run the code. I follow the logic of speech brain to write the whole repo.