to use magenta-js with this ddsp.
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.4k
- Forks
- 384
- PR merge metrics
- No merged PRs in 30d
Description
Hi.
I'd trained this ddsp model with my own dataset with ddsp.training.models.Autoencoder(). I'd like to use magenta-js with my own model. This magenta-js needs model.json, for example model.json.
Is there a way to export this checkpoint?
From the model.ts and toneTransfer, is that model.json link is for model architecture, or checkpoint weights?
Thanks.
Contributor guide
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 with the ddsp.training.models.Autoencoder checkpoint and compare it with the linked magenta-js model.ts and toneTransfer entry points. Determine whether the referenced model.json contains architecture, checkpoint weights, or both, and identify the export path needed for a user-trained model to work with magenta-js.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- javascript, python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100