Tao Liu

TTS-arxiv-daily. Automatically Update Text-to-speech (TTS) Papers Daily using Github Actions (Update Every 12th hours)

talking-face-arxiv-daily. 🎓 Update Talking-Face Research Papers Daily

talking_face_preprocessing. Preprocessing Scipts for Talking Face Generation

DiffDub. [ICASSP 2024] DiffDub: Person-generic visual dubbing using inpainting renderer with diffusion auto-encoder

LivePortrait-Train. Unoffical LivePortrait Training Script [ 🚧 Under Construction]

AwesomeDiarizationDataset. Both audio-only and audio-visual speaker diarization datasets are listed here.

Vibe_XASR. Swift

DiarizationVisualization. Visualization tools for audio-only and multi-modal speaker diarization dataset

Video-Generation-arxiv-daily. Automatically Update Video Generation Papers Daily using Github Actions (Update Every 12th hours)

DiarizationMetricInOne. Diarization Metric in One: current support DER, JER, CDER, SER, and BER

SD-arxiv-daily. Automatically Speaker Diarization (SD) Papers Daily using Github Actions (Update Every 12th hours)

AwesomeTokenizer. MultiModal Tokenizer Resources

EEND_PyTorch. A PyTorch implementation of End-to-End Neural Diarization

Multi-modal-Speech-Dataset. Multi-modal Speech Dataset

talking_face_evaluation_metrics.

talking_face_datasets.

EDTalk_facesr. [ECCV 2024] EDTalk - PyTorch Implementation with Face SR (512*512)

dscore-ovl. Detailed information for diarization metric: dscore, including errors in overlapped part.

BER. Balanced Error Rate for Speaker Diarization

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

EMOPortraits. Add Video Reenactment Pipeline to EMOPortraits

WorkflowVisualizer. A Workflow Visualizer For Claude Code