Sesame CSM Elise

This model is a fine-tuned version of sesame/csm-1b using the Elise dataset.

The model can be found here: keanteng/sesame-csm-elise

Model Details

• Base Model: sesame/csm-1b
• Training Data: MrDragonFox/Elise dataset
• Fine-tuning Approach: Voice cloning through conditional speech generation
• Voice Characteristics: [Describe voice qualities]
• Training Parameters:
  • Learning Rate: 2e-5
  • Epochs: 3
  • Batch Size: 1 with gradient accumulation steps of 4
• GPUs Used: 1x NVIDIA A100 40GB

Samples

Samples can be listened after downloading, you can find them here.

Using This Repo

Load the repo:

git clone https://github.com/keanteng/sesame-csm-elise/blob/main/requirements.txt

Install the requirements:

pip install -r requirements.txt