julianyulu / SyncNetCN
Optimized Syncnet and Chinese enhanced version, EN and CN checkpoints released
☆13Updated 3 years ago
Alternatives and similar repositories for SyncNetCN:
Users that are interested in SyncNetCN are comparing it to the libraries listed below
- ☆24Updated 3 years ago
- wav2lip in a Vector Quantized (VQ) space☆28Updated last year
- SyncTalkFace: Talking Face Generation for Precise Lip-syncing via Audio-Lip Memory☆33Updated 2 years ago
- PersonaTalk Hack☆13Updated 3 months ago
- ☆28Updated last year
- 复现Wav2Lip作者新的论文☆20Updated last year
- Spliting the ASR probability distribution results into the chinese pinyin, so as to extract more effective feature for the chinese speech…☆21Updated 2 years ago
- [ICCV2023] Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video☆71Updated last year
- Preprocessing Scipts for Talking Face Generation☆88Updated 3 months ago
- R2-Talker: Realistic Real-Time Talking Head Synthesis with Hash Grid Landmarks Encoding and Progressive Multilayer Conditioning☆80Updated last year
- 实现基于4k视频的高分辨率人物换衣、虚拟试穿、物品替换☆54Updated 2 years ago
- wav2lip训练数据预处理综合工具☆40Updated last year
- ☆27Updated last year
- simple and fast wav2lip using onnx models for face-detection and inference. Easy installation☆24Updated 6 months ago
- One-shot Audio-driven 3D Talking Head Synthesis via Generative Prior, CVPRW 2024☆60Updated 6 months ago
- Something about Talking Head Generation☆32Updated last year
- Talking head animation☆27Updated last year
- 基于DINet的推理服务，推理视频流和视频☆15Updated last year
- ☆14Updated last year
- Project page for "Improving Few-shot Learning for Talking Face System with TTS Data Augmentation" for ICASSP2023☆86Updated last year
- ☆32Updated last year
- ☆10Updated 2 years ago
- ☆51Updated last year
- ☆22Updated last year
- Considering the original Wav2Lip was trained on LSR2 and didn't have good performance on Chinese. I preprocessed CMLR Dataset and would t…☆60Updated last year
- 📖 A curated list of resources dedicated to avatar.☆58Updated 5 months ago
- 这是一个在wav2lip，使用wav2lip、gfpgan、yolov5等模型用RT加速的超快推理！经测试在2070显卡上可达到0.03秒每帧实现实时推理。☆27Updated last year
- [ICIAP 2023] Learning Landmarks Motion from Speech for Speaker-Agnostic 3D Talking Heads Generation☆62Updated last year
- Wav2Lip-Emotion extends Wav2Lip to modify facial expressions of emotions via L1 reconstruction and pre-trained emotion objectives. We als…☆96Updated 2 years ago
- Official repository for the paper VocaLiST: An Audio-Visual Synchronisation Model for Lips and Voices☆66Updated last year