Hugging Face's logo

TLME
/
RVC-Umamusume

Audio-to-Audio
Model card Files Community
1
TLME commited on
Commit
697f6eb
·
1 Parent(s): e606461

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -1,5 +1,7 @@
1
  ---
2
  license: mit
 
 
3
  ---
4
 
5
  # RVC-Umamusume
@@ -16,4 +18,6 @@ Umamusume charcters RVC models.
16
  Each model was trained for 100 epochs with batch size of 12, averaging 40 steps per epoch.
17
  On average, each character was trained using 10 to 20 minutes of voice data.
18
 
19
- If you think the performance of the model I created is not good, I have open-sourced the dataset, and you can train it yourself.
 
 
 
1
  ---
2
  license: mit
3
+ datasets:
4
+ - TLME/Umamusume-voice-transcription
5
  ---
6
 
7
  # RVC-Umamusume
 
18
  Each model was trained for 100 epochs with batch size of 12, averaging 40 steps per epoch.
19
  On average, each character was trained using 10 to 20 minutes of voice data.
20
 
21
+ If you think the performance of the model I created is not good, I presented the dataset, and you can train it yourself.
22
+
23
+ The majority of characters' voices come from :[Umamusume-voice-transcription](https://huggingface.co/datasets/TLME/Umamusume-voice-transcription), while a small portion of characters' voices come from: [zomehwh/tttttttt ](https://huggingface.co/datasets/zomehwh/tttttttt/tree/main).