batch execution of nllb translation
Open
- Dominant language
- Python
- Stars
- 7
- Forks
- 7
- PR merge metrics
- No merged PRs in 30d
Description
nllb can translate at one a list of source sentences, esp, in the presence of gpu seems it gives speedup. We need to break the set of input reviews into batches and call nllb to balance speed and memory size.
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by locating the code that invokes NLLB for review translation and tracing where the full set of input reviews is passed. Investigate the available GPU and memory behavior and any existing translation tests. Done means reviews are processed in batches while balancing translation speed and memory usage.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, performance
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100