Add sample audio and LFS rule for mp3

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp3 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -31,6 +31,12 @@ finetuned from a U.S. English base, and `it_IT-riccardo-x_low`, trained from scr
 quality — neither exposes a trainable checkpoint). This is the only public Italian **medium**
 checkpoint that can be used as a finetuning base.
 
+## Sample
+
+Audio of the base voice (it_IT-serena-medium):
+
+<audio controls src="samples/speaker_0.mp3"></audio>
+
 ## Use as a base for finetuning other Italian voices
 
 Any checkpoint of the same quality config (medium) can be resumed with piper_train:

samples/speaker_0.mp3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a662ec2d2bf393ef2175a8eb79b0e30c73605acea316ed772d355bb2053444
+size 166809