Update README.md

README.md

@@ -82,11 +82,11 @@ dump_wav('cm_music_piece.wav', audio, sample_rate=44100, use_int16=True)
 ```
 
 ## Limitations
-- For the music tasks, the model currently only supports strict format and close-ended instructions. If we have more funding, we plan to create a more diverse multi-turn music instruction chat data for better generalization.
+- The model currently only supports strict format and close-ended instructions for the music tasks. If we have more funding, we plan to create a more diverse multi-turn music instruction chat data for better generalization.
 - The model suffers from hallucinations, and shouldn't be used for music education. It could be improved by feeding more music textbooks, blogs, etc. And RLHF may help, too.
-- A large portion of the training data is in the style of Irish music. If possible, the community should develop a converter between performance midi and ABC scores.
+- A large portion of the training data is in the style of Irish music. If possible, the community should develop a converter between performance midi and ABC scores, so that we can include more established midi datasets.
 - The MusicThoeryBench results reported in the paper are obtained with perplexity mode. Direct generation may result in a worse performance.
-- We observe that using current version of training data, ChatMusician presents a weak in-context-learning and chain-of-thoughts ability. The community should work on improving the music data quality. 
+- We observe that using the current version of training data, ChatMusician presents a weak in-context-learning and chain-of-thoughts ability. The community should work on improving the music data quality. 
 
 ## Example Prompts