Snowad commited on
Commit
bdecc0a
1 Parent(s): 9c40e61

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -8,9 +8,10 @@ tags:
8
  - text-to-speech
9
  ---
10
 
 
11
 
12
- **V2.5 Model : Comming Soon™**
13
- Fine tune of my V2 model on all CommonVoice dataset, it made the voice clone better from the V2 model, I will train it more in the next days
14
 
15
  **V2 Model :**
16
 
 
8
  - text-to-speech
9
  ---
10
 
11
+ I stop training tortoise models because this technology is just outdated and too slow, I'm still the first one to want a good French TTS and I watch every day if new ambitious project is born and I won't hesitate to create a new hugging face project!
12
 
13
+ **V2.5 Model :**
14
+ Fine tune of my V2 model on all CommonVoice dataset (517k sample) on 2.5k step (batch size 200), Voice cloning has improved a bit but is still not great. However, if you fine tune this model on your own personality dataset then you can get pretty good results. A good V3 model would be to fine tune for like 50k steps on this dataset and I think there would be a way to get good results but I won't try
15
 
16
  **V2 Model :**
17