Add note on TSUM and the base model

README.md

@@ -26,8 +26,7 @@ Identical to base model.
 
 ## Training Data
 
-This model has been fine-tuned on the same AMI and ICSI text summarization data from the training data of the base
-model.
+This model has been fine-tuned on the text summarization data from the AMI and ICSI corpora. Note that the [base model](https://huggingface.co/meetween/Llama-speechlmm-1.0-l) was not trained on TSUM, so this is a new task.
 
 ## Evaluation Results