Update README.md

README.md

@@ -12,7 +12,7 @@ on the training subset of the Fisher corpus.
 * Foundation model: [unsloth/llama-3-8b-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit)
 * Finetuning scripts: https://github.com/google/speaker-id/tree/master/DiarizationLM/unsloth
 
-This difference between this model and [google/DiarizationLM-8b-Fisher-v1](https://huggingface.co/google/DiarizationLM-8b-Fisher-v1):
+The difference between this model and [google/DiarizationLM-8b-Fisher-v1](https://huggingface.co/google/DiarizationLM-8b-Fisher-v1):
 
 * For this model, the loss is only computed on the completion tokens.
 * For `google/DiarizationLM-8b-Fisher-v1`, the loss is computed also on the prompt tokens.