Update samples/python/multinomial_causal_lm/README.md

Co-authored-by: Zlobin Vladimir <[email protected]>

samples/python/multinomial_causal_lm/README.md

@@ -26,7 +26,7 @@ See https://github.com/openvinotoolkit/openvino.genai/blob/master/src/README.md#
 
 ## Streaming
 
-This Python example demonstrates custom detokenization with bufferization. The streamer receives integer tokens corresponding to each word or subword, one by one. If tokens are decoded individually, because of detokenize(tokenize(" a")) == "a" the resulting text will miss necessary spaces.
+This Python example demonstrates custom detokenization with bufferization. The streamer receives integer tokens corresponding to each word or subword, one by one. If tokens are decoded individually, the resulting text misses necessary spaces because of detokenize(tokenize(" a")) == "a".
 
 To address this, the detokenizer needs a larger context. We accumulate tokens in a tokens_cache buffer and decode multiple tokens together, adding the text to the streaming queue only when a complete decoded chunk is ready. We run a separate thread to print all new elements arriving in this queue from the generation pipeline. Each generated chunk of text is put into a synchronized queue, ensuring that all put and get operations are thread-safe and blocked until they can proceed.