~~Our co-speech generation dataset contains training and validation videos for **4** different IDs (PersonA, PersonB, PersonC, and PersonD), each video contains a single speaker, PersonA and PersonB speak Chinese, PersonC and PersonD speak English. The training videos last for at least 5 minutes with a resolution of 2160×3840 and the validation videos last for at least 1 minute with a resolution of 2160×3840. ~~

**Update: 2023-12-01**


Our co-speech generation dataset contains training and validation videos for **2** different IDs (PersonA, PersonB), each video contains a single speaker, PersonA and PersonB speak Chinese. The training videos last for at least 5 minutes with a resolution of 2160×3840 and the validation videos last for at least 1 minute with a resolution of 2160×3840. 

The audio of the test set is also released for participants to generate their results for the competition.

###Note
1. We also notice that directly generating high-resolution 2D videos is very challenging and time-consuming, so in this competition, the participants may downsample to video resolution to 288×512 to train their model, we will evaluate the results with a resolution of 288×512.
1. This dataset can only be used for this competition.
1. Due to some legal issues, we fail to collect a suitable English dataset for this competition. As the competition will end within about 1 month, given little time left, we decide to use the 2 uploaded IDs only in this competition.