Update README.md

README.md

@@ -9,11 +9,15 @@ pipeline_tag: text-to-speech
 license: cc-by-4.0
 ---
 
-This is a test to see how to finetune F5 in italian
+This is an Italian finetune for F5-TTS
+Italian only so can't speak english properly
 
-Trained over 247+h hours of "train" split of facebook/multilingual_librispeech dataset, 6700 steps for Epoch:
+Trained over 247+h hours of "train" split of facebook/multilingual_librispeech dataset, 6717 steps for Epoch:
 - catastrophic failure (the model forgot english)
-- italian pronunciation not perfect
+- italian pronunciation not perfect (there are lot of checkpoints to let you play with and extend training, maybe with different datasets)
+
+# Current most trained model
+italian_59kh/model_250800.safetensors (almost 38 Epoch finisched)
 
 ## folder structure:
 ```