zzj1111 / Preprocessed-CMLR-Dataset-For-Wav2Lip
Considering the original Wav2Lip was trained on LSR2 and didn't have good performance on Chinese. I preprocessed CMLR Dataset and would train Wav2Lip on CMLR. Wish it would do better in Chinese.
☆59Updated last year
Related projects ⓘ
Alternatives and complementary repositories for Preprocessed-CMLR-Dataset-For-Wav2Lip
- wav2lip训练数据预处理综合工具☆36Updated last year
- ☆46Updated last year
- ☆67Updated last month
- ☆32Updated last year
- ☆31Updated last year
- This is a project about talking faces. We use 576X576 sized facial images for training, which can generate 2k, 4k, 6k, and 8k digital hum…☆49Updated 8 months ago
- Just a suturing monster project.☆37Updated last year
- ☆189Updated 10 months ago
- ☆37Updated 10 months ago
- ☆53Updated last year
- 优化wav2lip的执行步骤，将头脸分离、嘴型替换、回补背景三个步骤分离，添加gfpgan强化面部功能，实现提前解帧，流式循环处理，对接obs☆45Updated 5 months ago
- ☆30Updated 10 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。☆26Updated last year
- R2-Talker: Realistic Real-Time Talking Head Synthesis with Hash Grid Landmarks Encoding and Progressive Multilayer Conditioning☆78Updated 10 months ago
- 通过此代码可以免训练模型并通过轻量级服务器定制数字人形象☆99Updated 7 months ago
- 复现Wav2Lip作者新的论文☆20Updated last year
- ☆193Updated last year
- Full version of wav2lip-onnx including face alignment and face enhancement and more...☆70Updated last month
- An optimized pipeline for DINet reducing inference latency for up to 60% 🚀. Kudos for the authors of the original repo for this amazing …☆104Updated last year
- ☆24Updated 3 years ago
- Faster Talking Face Animation on Xeon CPU☆120Updated last year
- Simple and fast wav2lip using new 256x256 resolution trained onnx-converted model for inference. Easy installation☆27Updated last month
- This project fixes the Wav2Lip project so that it can run on Python 3.9. Wav2Lip is a project that can be used to lip-sync videos to audi…☆18Updated last year
- ☆36Updated last year
- ☆50Updated last year
- ☆11Updated last year