Video-Text-to-Text
Transformers
Safetensors
qwen2_5_omni
text-to-audio
multimodal
video-captioning
audio-visual
ugc
Instructions to use openinterx/UGC-VideoCaptioner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openinterx/UGC-VideoCaptioner with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForTextToWaveform processor = AutoProcessor.from_pretrained("openinterx/UGC-VideoCaptioner") model = AutoModelForTextToWaveform.from_pretrained("openinterx/UGC-VideoCaptioner") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,12 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- openinterx/UGC-VideoCap
|
| 5 |
+
metrics:
|
| 6 |
+
- bleu
|
| 7 |
+
- accuracy
|
| 8 |
+
base_model:
|
| 9 |
+
- Qwen/Qwen2.5-Omni-3B
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
paper: https://arxiv.org/abs/2507.11336
|