Update checkpoint

D_1642000.pth → D_191000.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb0b7fc90dcee66e95f68da224ce0a5880a45345ae5e7c3b6293d2c61639f4e
-size 564536506
+oid sha256:aae8184e99156f26e2fbd8e748e8aa26906a0dbba83ef627a252e29b8e75371d
+size 564535842

G_1642000.pth → G_191000.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d707c03236c35b9252018799cca2fbcd1ef4d4c7943e7acfb0524229af14a891
-size 480945612
+oid sha256:5b6acc4bccf4e942f02fa5e82ad806d3c29e925a9d4a58cedd84f160d0cbc1d1
+size 482123406

README.md

@@ -7,7 +7,7 @@ pipeline_tag: audio-to-audio
 
 # About
 
-This is a basic zero-shot voice conversion model trained with VITS + softhubert
+This is a basic zero-shot voice conversion model trained with VITS + contentvec
 
 See:
 
@@ -15,11 +15,13 @@ See:
 
 <https://github.com/quickvc/QuickVC-VoiceConversion>
 
+<https://github.com/auspicious3000/contentvec>
+
 # Speaker Similarity
 
 Computed with eval.py with Resemblyzer
 
 ```
 Original QuickVC (trained on VCTK)       Average: 0.667 Min: 0.477
-New model                                Average: 0.836 Min: 0.692
-```
+New model                                Average: 0.880 Min: 0.712
+```