Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
metrics:
|
| 3 |
+
- cer
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
## Introduction
|
| 7 |
+
|
| 8 |
+
This repository provides the baseline model files for CNVSRC2024 (Chinese Continuous Visual Speech Recognition Challenge 2024).
|
| 9 |
+
|
| 10 |
+
## Usage
|
| 11 |
+
|
| 12 |
+
Please download these model files and use them in the [baseline code](https://github.com/sectum1919/CNVSRC2024Baseline).
|
| 13 |
+
|
| 14 |
+
## Performance
|
| 15 |
+
|
| 16 |
+
The following table shows these models' performance on their own tasks.
|
| 17 |
+
| Training Data | Task | CER | File Name |
|
| 18 |
+
|:-------------------------:|:----------------------:|:------:|:-----------------------------------------|
|
| 19 |
+
| CN-CVS (<4s) | Pre-training | / | model_avg_14_23_cncvs_4s.pth |
|
| 20 |
+
| CN-CVS (full) | Pre-training | / | model_avg_last10_cncvs_4s_30s.pth |
|
| 21 |
+
| CN-CVS + CNVSRC-Single.Dev| Single-speaker VSR (T1)| 39.66% | model_avg_last5_cncvs_cnvsrc-single.pth |
|
| 22 |
+
| CN-CVS + CNVSRC-Multi.Dev | Multi-speaker VSR (T2)| 52.20% | model_avg_last5_cncvs_cnvsrc-multi.pth |
|