yizhilll / MERT

Official implementation of the paper "Acoustic Music Understanding Model with Large-Scale Self-supervised Training".

yizhilll/MERT Issues

Questions about data preparation
Updated 3 months ago
will you provide fairseq checkpoints, so that tokenization from MERT is possible without retrain a clustering model?
Closed 3 months ago1
Fairseq Checkpoint
Closed 3 months ago1
When jointly mapping different modal features to the same semantics, which layer of the hidden layer is more appropriate to select
Closed 3 months ago1
How to convert a fairseq checkpoint to a huggingface checkpoint
Closed 3 months ago1
Reproducing the numbers
Updated 7 months ago
Which embedding to use for the downstream task of genre classification?
Closed 8 months ago1
questions about dictionary.encode_line to process encodec labels
Updated 8 months ago6
What is the sampling rate during training? Is it okay to upsample 16k to 24k during testing?
Closed 8 months ago1
Regarding attention relaxation
Updated 8 months ago
Will the tokens be released in the future?
Closed 9 months ago1
finetuned model for downstream tasks?
Closed a year ago1
High vram usage for long audio.
Updated a year ago1
ModuleNotFoundError: No module named 'datasets'
Closed a year ago