| from datasets import interleave_datasets | |
| from itertools import islice | |
| en_dataset = load_dataset('oscar', "unshuffled_deduplicated_en", split='train', streaming=True) | |
| fr_dataset = load_dataset('oscar', "unshuffled_deduplicated_fr", split='train', streaming=True) | |
| multilingual_dataset = interleave_datasets([en_dataset, fr_dataset]) |