LAION-AI / LAION-AI/CLAP

Missing about configs for pretrained model

Open
#120 2 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2.3k
Forks
213
PR merge metrics
No merged PRs in 30d

Description

Hello guys, i want to use the pretrained model for music(can be download from https://huggingface.co/lukewys/laion_clap/blob/main/music_audioset_epoch_15_esc_90.14.pt), but i do not know which is the config about this pretrained model(eg: the name of amodel and tmodel). I think i need the config files for every pretrained model.

And further, i try to guess some information about the config through model params. For the music model metioned above maybe have amodel of htsat-base and robert, but i am not sure if i miss some other important params. Because i test some music data from youtube, the map@10 is very low(about only 0.03).

Who can give me a config file about this model??

Thank for the CLAP team and it is a GREAT work !!

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No repository file or test is named. Start by examining the linked Hugging Face checkpoint and comparing its parameters with the project's existing pretrained-model configuration conventions; done means the checkpoint has a reliable configuration covering the required model parameters and the configuration is available for users.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.