# ValueError loading Helsinki-NLP tokenizers

**URL:** <https://discuss.huggingface.co/t/valueerror-loading-helsinki-nlp-tokenizers/174192>\
**Category:** 🤗Tokenizers\
**Created:** [March 11, 2026, 3:43pm UTC](https://discuss.huggingface.co/t/valueerror-loading-helsinki-nlp-tokenizers/174192 "2026-03-11T15:43:55Z")\
**Posts on this page:** 1\
**Showing post:** 4

<div class="post-metadata">

**Author:** ![bogolese](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/bogolese/32/53040_2.png) [@bogolese](https://discuss.huggingface.co/u/bogolese)\
**Post date:** [March 12, 2026, 1:02pm UTC](https://discuss.huggingface.co/t/valueerror-loading-helsinki-nlp-tokenizers/174192/4 "2026-03-12T13:02:44Z")

</div>

Thank you. Yes, I did get the sentencepiece error when I initially switched to MarianTokenizer.from\_pretrained(), but all hunky dory once I installed it.

Now my issue is that these models don’t work with DataParallel anymore, but that is another issue ([174223](https://discuss.huggingface.co/t/helsinki-nlp-throws-stopiteration-within-dataparallel/174223))(throws a StopTermination attempting to access self.model.device in its bowels). I may have to hand-jam my own threads for parallel inference (I had to do that for the ModernBERT models a while back, so code reuse is king!).

---

_[View the full topic](https://discuss.huggingface.co/t/valueerror-loading-helsinki-nlp-tokenizers/174192)._