FInetuning from a pretrained ckpt
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.3k
- Forks
- 213
- PR merge metrics
- No merged PRs in 30d
Description
Hello,
I am trying to finetune CLAP for a audio to text retrieval task, and I have formatted the datasets accordingly. I am facing issue to load the pretrained ckpts. I understand that the pretrained ckpt is loaded from the --pretrained arg but the model additionally needs a --amodel flag. How do I know which pretrained ckpt corresponds to which amodel?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing how the pretrained checkpoint is selected through --pretrained and how the required --amodel value is defined in the project. Trace the checkpoint-loading path and its available model names; the work is done when each pretrained checkpoint’s corresponding amodel is documented or the loading guidance is made unambiguous.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100