Commit
•
ef71f2a
1
Parent(s):
986223b
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,23 @@
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: openrail
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
|
| 3 |
---
|
| 4 |
license: openrail
|
| 5 |
---
|
| 6 |
+
Another model aside from Princess Bubblegum, I made a model for Flame Princess since she's a
|
| 7 |
+
rapper since Season 10 on Adventure Time. So why not give her a shot to make one for her?
|
| 8 |
+
I think she can sing Eminem's song if she can.
|
| 9 |
+
|
| 10 |
+
Trained her in 125 epochs, using RMVPE algorithm.
|
| 11 |
+
Datasets: 14 minutes from her 13 major episode appearances.
|
| 12 |
+
|
| 13 |
+
Also, my tablet overheated so bad for finding samples for FP since she's a hot momma.
|
| 14 |
+
What a coincidence hehehe.
|
| 15 |
+
|
| 16 |
+
Also, it's still certified pinoy-made model by KennyFromPH.
|
| 17 |
+
My Channel: https://youtube.com/@KennyFromPH07
|
| 18 |
+
|
| 19 |
+
I don't wanna make an epoch update anymore since I'm tired of waiting. Also my tablet's performance is now
|
| 20 |
+
deteriorating for being awake for hours without restarting. I used UVR5 Colab Edition for vocal isolation
|
| 21 |
+
this time, and yes I still trained the model in my old tablet. Also, it takes me 3 times since the
|
| 22 |
+
'train feature index' refuses to train the index file. So, I have to reprocess the dataset, then
|
| 23 |
+
re-extract the pitch extraction all over to add the index desperately.
|