Update README.md

README.md

@@ -20,6 +20,9 @@ The model is designed to be used to normalise 17th c. French texts. The best per
 The model is to be used with the custom pipeline available in in the original repository [here](https://github.com/rbawden/ModFr-Norm/blob/main/hf-conversion/pipeline.py) and in this repository [here](https://huggingface.co/rbawden/modern_french_normalisation/blob/main/pipeline.py). You first need to download the pipeline file so that you can use it locally (since it is not integrated into HuggingFace).
 
 ```
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from pipeline import NormalisationPipeline # N.B. local file
+
 tokeniser = AutoTokenizer.from_pretrained("rbawden/modern_french_normalisation")
 model = AutoModelForSeq2SeqLM.from_pretrained("rbawden/modern_french_normalisation")
 norm_pipeline = NormalisationPipeline(model=model, tokenizer=tokeniser, batch_size=batch_size,beam_size=beam_size)