update init app, intro first common file for refactoring

app.py

@@ -1,4 +1,5 @@
 import transformers
+import hscommon
 
 import gradio as gr
 import tensorflow as tf
@@ -30,27 +31,14 @@ def compile_model(model):
     model.compile(optimizer=optimizer, loss=LOSS, metrics=[METRICS])
     return model
 
-hs_detection_model = tf.keras.models.load_model(MODEL_DIRECTORY, compile=False)  #tf.keras.models.load_model('save/kerasmodel/model.h5') #tf.saved_model.load('save/model') #tf.keras.models.load_model('save/model')
+hs_detection_model = tf.keras.models.load_model(MODEL_DIRECTORY, compile=False)
 compile_model(hs_detection_model)
 
-def encode(sentences):
-    return TOKENIZER.batch_encode_plus(
-        sentences,
-        max_length=MAX_SEQUENCE_LENGTH, # set the length of the sequences
-        add_special_tokens=True, # add [CLS] and [SEP] tokens
-        return_attention_mask=True,
-        return_token_type_ids=False, # not needed for this type of ML task
-        pad_to_max_length=True, # add 0 pad tokens to the sequences less than max_length
-        return_tensors='tf'
-    )
-
 def inference(sentence):
-    print(sentence)
-    encoded_sentence = encode([sentence])
-    print(encoded_sentence)
+    encoded_sentence = hscommon.encode([sentence], TOKENIZER, MAX_SEQUENCE_LENGTH)
     predicition = hs_detection_model.predict(encoded_sentence.values())
-    print(predicition)
     return predicition
 
-iface = gr.Interface(fn=inference, inputs="text", outputs="text") #, live=True)
+input_sentence_text = gr.inputs.Textbox(placeholder="Hier den Satz eingeben, der Hassrede enthalten kann.")
+iface = gr.Interface(fn=inference, inputs=input_sentence_text, outputs="text")
 iface.launch()

hscommon.py

@@ -0,0 +1,13 @@
+
+
+
+def encode(sentences, tokenizer, sequence_length):
+    return tokenizer.batch_encode_plus(
+        sentences,
+        max_length=sequence_length, # set the length of the sequences
+        add_special_tokens=True, # add [CLS] and [SEP] tokens
+        return_attention_mask=True,
+        return_token_type_ids=False, # not needed for this type of ML task
+        pad_to_max_length=True, # add 0 pad tokens to the sequences less than max_length
+        return_tensors='tf'
+    )