vsro200 commited on
Commit
4195b93
·
verified ·
1 Parent(s): 674d977

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -4
README.md CHANGED
@@ -8,10 +8,7 @@ This repository contains the model checkpoints for the paper **"VSRo-200: A Roma
8
 
9
  These models are fine-tuned versions of MultiVSR, specifically trained for the Romanian language. We provide various checkpoints to demonstrate the impact of dataset size, annotation quality (human-annotated vs. automatically generated pseudo-labels), and gender distribution on VSR performance.
10
 
11
-
12
- ## 📊 Accompanying Dataset
13
- The models were trained and evaluated on the **RoVSR Dataset** (Romanian Visual Speech Recognition Dataset), a 200-hour corpus of Romanian podcasts.
14
- * **Dataset Link:** [vsro200/vsro200_dataset](https://huggingface.co/datasets/vsro200/vsro200_dataset)
15
 
16
  ## 📂 Repository Structure
17
  All model checkpoints are stored in the `checkpoints/` directory. The naming convention follows the pattern: `model_[hours]_[type].pt`.
 
8
 
9
  These models are fine-tuned versions of MultiVSR, specifically trained for the Romanian language. We provide various checkpoints to demonstrate the impact of dataset size, annotation quality (human-annotated vs. automatically generated pseudo-labels), and gender distribution on VSR performance.
10
 
11
+ The models were trained and evaluated on the **VSRo Dataset**, a 200-hour corpus of Romanian podcasts.
 
 
 
12
 
13
  ## 📂 Repository Structure
14
  All model checkpoints are stored in the `checkpoints/` directory. The naming convention follows the pattern: `model_[hours]_[type].pt`.