Hi there 👋 AI Research Engineer Research Areas Automatic Dubbing Lip Synchronization Multimodal Large Language Models Neural Codec Language model base text to speech Contributed repos: mmsegmentation Support Delving into High-Quality Synthetic Face Occlusion Segmentation Datasets Fix mmseg.api.inference inference_segmentor oslo Distributed Data Parallel Tutorials for DDP, Zero controlnet_aux canny, midas, mediapipe face, SAM, mobileSAM diffusers Support different strength for Stable Diffusion TensorRT inpainting axolotl streaming multipack for pretraining dataset Scheduler implementation of Continual Pre-Training of Large Language Models: How to (re)warm your model?