Update README.md

README.md

@@ -1,17 +1,16 @@
 ---
 language:
-  - en
+- en
 thumbnail: null
 tags:
-  - image-classification
-  - multimodal
-  - tensorflow
+- image-classification
+- multimodal
+- tensorflow
 license: mit
 datasets:
-  - 'flex_civ_vi_screens'
-pipeline_tag: image-classification
+- flex_civ_vi_screens
+pipeline_tag: audio-text-to-text
 library_name: tensorflow
-
 ---
 
 # Multimodal Classification Model (BM-v1)
@@ -30,4 +29,4 @@ This model combines text and image inputs to perform classification tasks using
 
 ### Direct Use
 
-The model is designed for multimodal classification tasks that require both image and text inputs. Example usage:
+The model is designed for multimodal classification tasks that require both image and text inputs. Example usage: