922CA commited on
Commit
4ac7bb3
1 Parent(s): 9218648

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -5
README.md CHANGED
@@ -7,30 +7,42 @@ Test RVC2 models on the DDLC character Monika, via various hyperparams and datas
7
  # monika-test-0 (~07/2023)
8
  * Trained on augmented dataset of ~10 10 second clips
9
  * Trained for ~100 epochs
10
- * "Version 0"
 
11
 
12
  # monika-test-2 (~07/2023)
13
  * Trained on augmented dataset of ~10 10 second clips (augmented via tortoise tts)
14
  * Trained for 100 epochs
 
15
 
16
  # monika-test-4 (~07/2023)
17
  * Trained on smaller but better dataset of ~2 10 second clips (augmented via 11labs)
18
  * Trained for 150 epochs
 
19
 
20
  # monika-test-7 (08/22/2023)
21
  * Trained on augmented dataset of ~10+ 10 second clips (augmented via tortoise tts)
22
  * Trained for 60 epochs (720 steps)
23
  * Better quality than others
24
- * "Version 1"
 
25
 
26
  # monika-test-8 (08/22/2023)
27
  * Trained on smaller but better dataset of ~5 10 second clips (some augmented via 11labs)
28
  * Trained for 60 epochs (660 steps)
29
  * Even clearer quality but with slightly more artifacting than monika-test-7 (still better than pre 7th ones)
30
- * "Version 1a"
 
31
 
32
  # ct-m4 (~10/2023)
33
  * Trained on preprocessed version of dataset of ~5 10 second clips
34
  * Trained for ~200 epochs
35
- * Should be even clearer quality
36
- * WIP
 
 
 
 
 
 
 
 
7
  # monika-test-0 (~07/2023)
8
  * Trained on augmented dataset of ~10 10 second clips
9
  * Trained for ~100 epochs
10
+ * RVC1
11
+ * "Version 1" ("0" in the old numbering)
12
 
13
  # monika-test-2 (~07/2023)
14
  * Trained on augmented dataset of ~10 10 second clips (augmented via tortoise tts)
15
  * Trained for 100 epochs
16
+ * RVC1
17
 
18
  # monika-test-4 (~07/2023)
19
  * Trained on smaller but better dataset of ~2 10 second clips (augmented via 11labs)
20
  * Trained for 150 epochs
21
+ * RVC1
22
 
23
  # monika-test-7 (08/22/2023)
24
  * Trained on augmented dataset of ~10+ 10 second clips (augmented via tortoise tts)
25
  * Trained for 60 epochs (720 steps)
26
  * Better quality than others
27
+ * "Version 2" ("1" in old numbering)
28
+ * RVC2
29
 
30
  # monika-test-8 (08/22/2023)
31
  * Trained on smaller but better dataset of ~5 10 second clips (some augmented via 11labs)
32
  * Trained for 60 epochs (660 steps)
33
  * Even clearer quality but with slightly more artifacting than monika-test-7 (still better than pre 7th ones)
34
+ * "Version 2a" ("1a" in old numbering)
35
+ * RVC2
36
 
37
  # ct-m4 (~10/2023)
38
  * Trained on preprocessed version of dataset of ~5 10 second clips
39
  * Trained for ~200 epochs
40
+ * Test model
41
+ * RVC1
42
+
43
+ # ct-m4 (~10/2023)
44
+ * Trained on preprocessed version of dataset of ~5 10 second clips
45
+ * Trained for ~200 epochs
46
+ * "Version 4" ("3" in old numbering)
47
+ * RVC2, WIP
48
+