add app

app.py

@@ -6,73 +6,97 @@ from transformers import AutoTokenizer, BertForSequenceClassification, AutoModel
 from transformers import TextClassificationPipeline
 import gradio as gr
 
-# global var
-MODEL_NAME = 'momo/KcBERT-base_Hate_speech_Privacy_Detection'
-tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+tokenizer = AutoTokenizer.from_pretrained('momo/KcELECTRA-base_Hate_speech_Privacy_Detection')
 model = AutoModelForSequenceClassification.from_pretrained(
-    MODEL_NAME,
+    'momo/KcELECTRA-base_Hate_speech_Privacy_Detection',
     num_labels= 15,
     problem_type="multi_label_classification"
 )
-# config = AutoConfig.from_pretrained(MODEL_NAME)
 
-MODEL_BUF = {
-    "name": MODEL_NAME,
-    "tokenizer": tokenizer,
-    "model": model,
-    # "config": config
-}
 
-def change_model_name(name):
-    MODEL_BUF["name"] = name
-    MODEL_BUF["tokenizer"] = AutoTokenizer.from_pretrained(name)
-    MODEL_BUF["model"] = AutoModelForSequenceClassification.from_pretrained(name)
-    # MODEL_BUF["config"] = AutoConfig.from_pretrained(name)
+pipe = TextClassificationPipeline(
+model = model,
+tokenizer = tokenizer,
+return_all_scores=True,
+function_to_apply='sigmoid'
+)
+
+def predict(text):
+  return pipe(text)[0]["translation_text"]
+
+iface = gr.Interface(
+  fn=predict, 
+  inputs='text',
+  outputs='text',
+  examples=[["Hello! My name is Omar"]]
+)
+
+iface.launch()
+
+
+
+# # global var
+# MODEL_NAME = 'momo/KcBERT-base_Hate_speech_Privacy_Detection'
+# tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+# model = AutoModelForSequenceClassification.from_pretrained(
+#     MODEL_NAME,
+#     num_labels= 15,
+#     problem_type="multi_label_classification"
+# )
+
+# MODEL_BUF = {
+#     "name": MODEL_NAME,
+#     "tokenizer": tokenizer,
+#     "model": model,
+# }
 
+# def change_model_name(name):
+#     MODEL_BUF["name"] = name
+#     MODEL_BUF["tokenizer"] = AutoTokenizer.from_pretrained(name)
+#     MODEL_BUF["model"] = AutoModelForSequenceClassification.from_pretrained(name)
 
-def predict(model_name, text):
-    if model_name != MODEL_BUF["name"]:
-        change_model_name(model_name)
+# def predict(model_name, text):
+#     if model_name != MODEL_BUF["name"]:
+#         change_model_name(model_name)
     
-    tokenizer = MODEL_BUF["tokenizer"]
-    model = MODEL_BUF["model"]
-    # config = MODEL_BUF["config"]
-
-    unsmile_labels = ["여성/가족","남성","성소수자","인종/국적","연령","지역","종교","기타 혐오","악플/욕설","clean", 'name', 'number', 'address', 'bank', 'person']
-    num_labels = len(unsmile_labels)
-
-    model.config.id2label = {i: label for i, label in zip(range(num_labels), unsmile_labels)}
-    model.config.label2id = {label: i for i, label in zip(range(num_labels), unsmile_labels)}
-
-    pipe = TextClassificationPipeline(
-    model = model,
-    tokenizer = tokenizer,
-    return_all_scores=True,
-    function_to_apply='sigmoid'
-    )
-
-    for result in pipe(text)[0]:
-        output = result
-
-    return output
-
-if __name__ == '__main__':
-    text = '읿딴걸 홍볿글 읿랉곭 쌑젩낄고 앉앟있냩'
-
-    model_name_list = [
-        'momo/KcELECTRA-base_Hate_speech_Privacy_Detection',
-        "momo/KcBERT-base_Hate_speech_Privacy_Detection",
-    ]
-
-    #Create a gradio app with a button that calls predict()
-    app = gr.Interface(
-        fn=predict,
-        inputs=[gr.inputs.Dropdown(model_name_list, label="Model Name"), 'text'], outputs=['label'], 
-        examples = [[MODEL_BUF["name"], text], [MODEL_BUF["name"], "4=🦀 4≠🦀"]],
-        title="한국어 혐오표현, 개인정보 판별기 (Korean Hate Speech and Privacy Detection)",
-        description="Korean Hate Speech and Privacy Detection."
-        )
-    app.launch()
+#     tokenizer = MODEL_BUF["tokenizer"]
+#     model = MODEL_BUF["model"]
+
+#     unsmile_labels = ["여성/가족","남성","성소수자","인종/국적","연령","지역","종교","기타 혐오","악플/욕설","clean", 'name', 'number', 'address', 'bank', 'person']
+#     num_labels = len(unsmile_labels)
+
+#     model.config.id2label = {i: label for i, label in zip(range(num_labels), unsmile_labels)}
+#     model.config.label2id = {label: i for i, label in zip(range(num_labels), unsmile_labels)}
+
+#     pipe = TextClassificationPipeline(
+#     model = model,
+#     tokenizer = tokenizer,
+#     return_all_scores=True,
+#     function_to_apply='sigmoid'
+#     )
+
+#     for result in pipe(text)[0]:
+#         output = result
+
+#     return output
+
+# if __name__ == '__main__':
+#     text = '읿딴걸 홍볿글 읿랉곭 쌑젩낄고 앉앟있냩'
+
+#     model_name_list = [
+#         'momo/KcELECTRA-base_Hate_speech_Privacy_Detection',
+#         "momo/KcBERT-base_Hate_speech_Privacy_Detection",
+#     ]
+
+#     #Create a gradio app with a button that calls predict()
+#     app = gr.Interface(
+#         fn=predict,
+#         inputs=[gr.inputs.Dropdown(model_name_list, label="Model Name"), 'text'], outputs=['label'], 
+#         examples = [[MODEL_BUF["name"], text], [MODEL_BUF["name"], "4=���� 4≠🦀"]],
+#         title="한국어 혐오표현, 개인정보 판별기 (Korean Hate Speech and Privacy Detection)",
+#         description="Korean Hate Speech and Privacy Detection."
+#         )
+#     app.launch()
     
 
 # # global var