git clone https://www.modelscope.cn/speechoceanadmin/CNVSRC2023Baseline.git
介绍
本仓库提供的模型文件是CNVSRC2023(Chinese Continuous Visual Speech Recognition Challenge 2023)挑战赛的基线系统对应的模型。
This repository provides the baseline model files for CNVSRC2023 (Chinese Continuous Visual Speech Recognition Challenge 2023).
使用
请配合基线系统代码baseline进行训练、微调或测试。
Please download these model files and use them in the baseline code.
模型性能
下面的表格中列出了每个模型在对应的挑战赛任务上的封闭赛道内的CER。
The following table shows these models' performance on their own tasks.
| Training Data | Task | CER | File Name |
|---|---|---|---|
| CN-CVS (<4s) | Pre-training | / | modelavg1423cncvs_4s.pth |
| CN-CVS (full) | Pre-training | / | modelavglast10cncvs4s_30s.pth |
| CN-CVS + CNVSRC-Single.Dev | Single-speaker VSR (T1) | 48.60% | modelavglast5cncvscnvsrc-single.pth |
| CN-CVS + CNVSRC-Multi.Dev | Multi-speaker VSR (T2) | 58.37% | modelavglast5cncvscnvsrc-multi.pth |
评论