Update README.md
Browse files
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`.
|