Ruibin Yuan

The detection score you provide is not normalized?

1

I find that the detection score you use is not normalized (not in the range of [0, 1]). Which layer or where did you extract those scores from? Are those...

Help with replicating the results for Hubert Pretraining

2

## ❓ Questions and Help #### What is your question? I am trying to replicate the HuBERT base pretraining iter1 on librispeech 960hr. However, the training curve seems to be...

Hi, we are researchers from the MAP (music audio pre-train) project. We pre-train transformer LMs on large-scale music audio datasets. See below. Our model, MERT, uses a similar method as...

i think the inpainting for general audio is ok. but for speech inpainting, there is still issue. check this command for tts inpainting, not working properly audioldm2 -t "A male...

Why clip_guided works better than text2im, inconsistent with the paper's claim?

2

I have tested the glide model for a few days (I tried many kinds of prompts), and my result is that clip_guided works better than classifier-free text2im. clip_guided can correctly...

Support our open source music pretrained Transformer

6

Hi, we are researchers from the MAP (music audio pre-train) project. We pre-train transformer LMs on large-scale music audio datasets. See below. Our model, MERT, uses a similar method as...