Add application file

app.py

@@ -147,45 +147,35 @@ def extract_abstract(text_per_pagy):
     return abstract_text
 
 
-def main_function(uploaded_file):
-    # Controlla se un file è stato effettivamente caricato
-    if uploaded_file is None:
+def main_function(uploaded_filepath):
+    #a control to see if there is a file uploaded
+    if uploaded_filepath is None:
         return "No file loaded", None
 
-    # Crea un file temporaneo per salvare il PDF caricato
-    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as temp_pdf:
-        temp_pdf.write(uploaded_file.read())
-        temp_pdf_path = temp_pdf.name
+    #read and process the file
+    text_per_pagy = read_pdf(uploaded_filepath)
 
-    # Utilizza il percorso del file temporaneo per leggere e processare il PDF
-    try:
-        text_per_pagy = read_pdf(temp_pdf_path)
+    #cleaning the text and getting the abstract
+    for key, value in text_per_pagy.items():
+        cleaned_text = clean_text(' '.join(value[0]))
+        text_per_pagy[key] = cleaned_text
+    abstract_text = extract_abstract(text_per_pagy)
 
-        # Pulisci il testo e estrai l'abstract
-        for key, value in text_per_pagy.items():
-            cleaned_text = clean_text(' '.join(value[0]))
-            text_per_pagy[key] = cleaned_text
-        abstract_text = extract_abstract(text_per_pagy)
+    #abstract summary
+    summarizer = pipeline("summarization", model="pszemraj/long-t5-tglobal-base-sci-simplify-elife")
+    summary = summarizer(abstract_text, max_length=50, min_length=30, do_sample=False)[0]['summary_text']
 
-        # Riassumi l'abstract
-        summarizer = pipeline("summarization", model="pszemraj/long-t5-tglobal-base-sci-simplify-elife")
-        summary = summarizer(abstract_text, max_length=50, min_length=30, do_sample=False)[0]['summary_text']
+    #generating the audio from the text, with my pipeline and model
+    synthesiser = pipeline("text-to-speech", model="microsoft/speecht5_tts")
+    embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
+    speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
+    speech = synthesiser(summary, forward_params={"speaker_embeddings": speaker_embedding})
 
-        # Genera l'audio dal riassunto
-        synthesiser = pipeline("text-to-speech", model="microsoft/speecht5_tts")
-        embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
-        speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
-        speech = synthesiser(summary, forward_params={"speaker_embeddings": speaker_embedding})
+    #saving the audio in a temp file
+    audio_file_path = "summary.wav"
+    sf.write(audio_file_path, speech["audio"], samplerate=speech["sampling_rate"])
 
-        # Salva l'audio in un file temporaneo
-        audio_file_path = "summary.wav"
-        sf.write(audio_file_path, speech["audio"], samplerate=speech["sampling_rate"])
-
-    finally:
-        # Elimina il file temporaneo
-        os.remove(temp_pdf_path)
-
-    # Restituisci testo e audio
+    #the function returns the 2 pieces we need
     return summary, audio_file_path