summa add

app.py

@@ -18,7 +18,7 @@ def speechToText(file):
 
     my_text = query(file)
 
-    sentences = my_text["text"].split(".")
+    #sentences = my_text["text"].split(".")
 
     
     def translate(sentences):
@@ -30,11 +30,33 @@ def speechToText(file):
 
         return text_translated
     
-    text_translate = translate(sentences)
+    #text_translate = translate(sentences)
 
     #combined_text = ' '.join([item['translation_text'] for sublist in text_translated for item in sublist])
 
-    return text_translate
+    def summa(my_text):
+        pipe = pipeline("summarization", model="facebook/bart-large-cnn")
+
+        max = 1024 
+        if len(my_text) > max:    
+            combined_text_parts = [my_text[i:i + max] for i in range(0, len(my_text), max)]
+        else:
+            combined_text_parts = [my_text]
+
+        summaries = []
+        for part in combined_text_parts:
+            summary = pipe(part, max_length=180, min_length=140, do_sample=False)
+            summaries.append(summary[0]['summary_text'])
+
+
+        full_summary = ' '.join(summaries)
+
+
+        return full_summary
+    
+    full_summaries = summa(my_text)
+
+    return full_summaries
 
 demo = gr.Interface(fn=speechToText, inputs="file", outputs="text")
 demo.launch()

requirements.txt

@@ -4,4 +4,5 @@ tensorflow>=2.0
 tf-keras
 sentencepiece
 python_multipart
+multipart
 requests_toolbelt