NLLB-inference
NLLB-inference copied to clipboard
Character translation limit?
The sentence buffer size is quoted at 100000, however I hit a limit at about 500 characters being translated, is this baked in somewhere?
Hi, buffer-size is simply set large enough to be greater than batch-size, it's not related to the generation result. Fairseq has a max_position=512 limit, maybe one of your input sentence reached this length limitation.