Instructions to use Helsinki-NLP/opus-mt-tr-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-tr-en with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tr-en")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-tr-en") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-tr-en") - Inference
- Notebooks
- Google Colab
- Kaggle
When any Devanagari script is input into this model it returns a vulgar reply.
#2
by coltonbehannon - opened
While accidentally uploading text to the wrong model I was very surprised by the result. This type of response appears to occur for any input that contains Devanagari script.