Update README.md
Browse files
README.md
CHANGED
@@ -10,10 +10,10 @@ tags:
|
|
10 |
|
11 |
**V1 :** I intend to train the model even more on a larger dataset and for longer
|
12 |
|
13 |
-
Tortoise base model Fine tuned on a custom multispeaker French dataset of 24k samples (SIWIS + Common Voice) on
|
14 |
|
15 |
**Inference :**
|
16 |
-
* You can use the model by downloading the "
|
17 |
|
18 |
**Fine tuning :**
|
19 |
* I used 152334H/DL-Art-School for training, if you want to resume training from my epoch, follow its documentation and download "5850.state"
|
|
|
10 |
|
11 |
**V1 :** I intend to train the model even more on a larger dataset and for longer
|
12 |
|
13 |
+
Tortoise base model Fine tuned on a custom multispeaker French dataset of 24k samples (SIWIS + Common Voice) on 8850 step with a RTX 3090 (~= 19 hours of training)
|
14 |
|
15 |
**Inference :**
|
16 |
+
* You can use the model by downloading the "8850_gpt.pth" model and use it in the tortoise-tts repo or one of its optimized forks (git.ecker.tech/mrq/ai-voice-cloning | 152334H/tortoise-tts-fast)
|
17 |
|
18 |
**Fine tuning :**
|
19 |
* I used 152334H/DL-Art-School for training, if you want to resume training from my epoch, follow its documentation and download "5850.state"
|