Update README.md

README.md

@@ -11,7 +11,7 @@ pipeline_tag: sentence-similarity
 
 ## Introduction
 
-BertChunker is a trained chunker for chunking text for RAG. It was trained based on [MiniLM-L6-H384-uncased](https://huggingface.co/nreimers/MiniLM-L6-H384-uncased) with an adapter. The whole training lasted for 10 minutes on a Nvidia P40 GPU on a 50 MB synthetized dataset.
+BertChunker is a trained chunker for chunking text for RAG. It was trained based on [MiniLM-L6-H384-uncased](https://huggingface.co/nreimers/MiniLM-L6-H384-uncased) with a classifier head to predict the start token of chunks. The whole training lasted for 10 minutes on a Nvidia P40 GPU on a 50 MB synthetized dataset.
 
 This repo includes model checkpoint, BertChunker class definition file and all the other files needed.
 
@@ -65,7 +65,7 @@ for i, c in enumerate(chunks):
     print(f'-----chunk: {i}------------')
     print(c)
 
-# chunk the text faster with a fixed context window, batchsize is the number of windows run per batch.
+# chunk the text faster, by using a fixed context window, batchsize is the number of windows run per batch.
 print('----->Here is the result of fast chunk method<------:')
 chunks=model.chunk_text_fast(text, tokenizer, batchsize=20, threshold=0)