Skip to content

Open-Sora: Democratizing Efficient Video Production for All

Python

add tagging

Tom Youngb59f5892dd1e
diff --git a/docs/data_processing.md b/docs/data_processing.md
index e9cf362..2c6b9c5 100644
--- a/docs/data_processing.md
+++ b/docs/data_processing.md
@@ -65,8 +65,13 @@ python -m tools.datasets.datautil \
--refine-llm-caption \
--remove-empty-caption \
--output ${ROOT_META}/meta_clips_caption_cleaned.csv
+
+# 4.4 Optionally generate tags (e.g., objects) based on the captions. This should output your_output_prefix_{key}.csv
+torchrun --nproc_per_node 8 --standalone -m tools.caption.caption_llama3 ${ROOT_META}/meta_clips_caption_cleaned.csv --key objects --output_prefix your_output_prefix
+
```
+
For more information, please refer to:
- [Dataset Management](../tools/datasets/README.md)
- [Scene Detection and Video Splitting](../tools/scene_cut/README.md)