Merge pull request #17 from jaelgu/main

Update text-embedding

text_embedding/description.yaml

@@ -74,7 +74,9 @@ models:
         op-name: "text_embedding.transformers"
         op-link: "https://towhee.io/text-embedding/transformers"
         pretrained-models:
-            - "text_embedding.transformers(model_name = '')"
+            - "text_embedding.transformers(model_name = 'camembert-base')"
+            - "text_embedding.transformers(model_name = 'Musixmatch/umberto-commoncrawl-cased-v1')"
+            - "text_embedding.transformers(model_name = 'Musixmatch/umberto-wikipedia-uncased-v1')"
     - canine:
         model: "CANINE"
         op-name: "text_embedding.transformers"
@@ -107,6 +109,10 @@ models:
             - "text_embedding.transformers(model_name = 'microsoft/deberta-base-mnli')"
             - "text_embedding.transformers(model_name = 'microsoft/deberta-large-mnli')"
             - "text_embedding.transformers(model_name = 'microsoft/deberta-xlarge-mnli')"
+            - "text_embedding.transformers(model_name = 'microsoft/deberta-v2-xlarge')"
+            - "text_embedding.transformers(model_name = 'microsoft/deberta-v2-xxlarge')"
+            - "text_embedding.transformers(model_name = 'microsoft/deberta-v2-xlarge-mnli')"
+            - "text_embedding.transformers(model_name = 'microsoft/deberta-v2-xxlarge-mnli')"
     - distilbert:
         model: "DistilBert"
         op-name: "text_embedding.transformers"
@@ -135,7 +141,10 @@ models:
         op-name: "text_embedding.transformers"
         op-link: "https://towhee.io/text-embedding/transformers"
         pretrained-models:
-            - "text_embedding.transformers(model_name = '')"
+            - "text_embedding.transformers(model_name = 'flaubert/flaubert_small_cased')"
+            - "text_embedding.transformers(model_name = 'flaubert/flaubert_base_uncased')"
+            - "text_embedding.transformers(model_name = 'flaubert/flaubert_base_cased')"
+            - "text_embedding.transformers(model_name = 'flaubert/flaubert_large_cased')"
     - fnet:
         model: "FNet"
         op-name: "text_embedding.transformers"

text_embedding/example.md

@@ -1,14 +1,9 @@
 ```python
 import towhee
 
-towhee.glob['path']('./teddy.jpg') \
-      .image_decode['path', 'img']() \
-      .image_text_embedding.clip['img', 'vec'](model_name='clip_vit_b32', modality='image') \
-      .select['img', 'vec']() \
-      .show()
-
-towhee.dc['text'](["A teddybear on a skateboard in Times Square."]) \
-      .image_text_embedding.clip['text','vec'](model_name='clip_vit_b32', modality='text') \
-      .select['text', 'vec']() \
-      .show()
+(
+    towhee.dc['text'](["Hello, world."])
+          .text_embedding.transformers['text', 'vec'](model_name="distilbert-base-cased")
+          .show()
+)
 ```

text_embedding/interface.md

@@ -1,10 +1,12 @@
 **Parameters:**
 
-**data:** *str or List[towhee.types.Image] (Image a sub-class of numpy.ndarray)*
+***text***: *str*
 
-Input text or video frames.
+​	The text in string.
 
-**Returns:** *numpy.ndarray*
 
-The embedding vector.
+**Returns**: *numpy.ndarray*
+
+​	The text embedding extracted by model.
+