metadata
license: apache-2.0
V1 : I intend to train the model even more on a larger dataset and for longer
Tortoise base model Fine tuned on a custom multispeaker French dataset of 24k samples (SIWIS + Common Voice) on 5850 step with a RTX 3090 (~= 14 hours of training)
Inference :
- You can use the model by downloading the "5850_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)
Fine tuning :
- I used 152334H/DL-Art-School for training, if you want to resume training from my epoch, follow its documentation and download "5850.state"