Update README.md

README.md

@@ -23,14 +23,18 @@ on the wiki.en dataset from [oliverguhr/spelling](https://github.com/oliverguhr/
 This an experimental model that should be capable of fixing typos and punctuation.
 
 ```python
-from transformers import pipeline
-fix_spelling = pipeline(
+pipe = pipeline(
     "text2text-generation",
     model="jbochi/flan-t5-base-spelling",
-    prefix="proofread: "
+    token=access_token
 )
-
-print(fix_spelling("lets do a comparsion",max_length=100))
+   
+def fix_spelling(input_sentence):
+    output = pipe("proofread: " + input_sentence, max_length=100)
+    return output[0]['generated_text']
+   
+print(fix_spelling("lets do a comparsion"))
+#lets do a comparison
 ```
 
 ## Intended uses & limitations
@@ -39,7 +43,7 @@ Intented for research purposes.
 
 - It may produce artifacts.
 - It doesn't support languages other than English.
-- It was fine-tuned with a `max_length` of 100.
+- It was fine-tuned with a `max_length` of 100 tokens.
 
 ## Training and evaluation data