Convert Ctranslate2 model to Pytorch or TorchScript or PyTorch Lightning
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 4.7k
- Forks
- 536
- Avg merge
- 12h 12m
- Merged PRs (30d)
- 4
Description
I want to inference NMT model on android device and found this for demo android application using pytorch lightning. I have a pretrained NMT model which was converted to Ctranslate2 using OpenNMTPy converter. But now don't have access to .pt anymore.
Any ideas on how it could be done?
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 by reading the linked pytorch/android-demo-app Seq2SeqNMT example and reviewing the available CTranslate2 model produced by the OpenNMTPy converter. Compare the example's expected PyTorch, TorchScript, or PyTorch Lightning artifacts with the available output; done would mean a demonstrated conversion path for Android or a documented limitation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- android, pytorch
- Domain
- machine-learning, mobile-dev
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100