ah indeed it seems that no truncation is enabled in the base Pipeline class: transformers/base.py at 8d43c71a1ca3ad322cc45008eb66a5611f1e017e 路 huggingface/transformers 路 GitHub
one alternative would be to extract the features directly from the model as described in this thread: Truncating sequence -- within a pipeline
this way you can enforce truncation=True with your tokenizer and pass the truncated inputs to the model