Update app.py to handle audio transcription and summarization

app.py

@@ -1,7 +1,7 @@
 import streamlit as st
-import soundfile as sf
-import numpy as np
 from transformers import pipeline
+import soundfile as sf
+import torch
 
 # Load Transcriber model optimized for CPU
 transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-tiny.en", device=-1)
@@ -9,32 +9,31 @@ transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-tin
 # Load Summary Model optimized for CPU
 summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6", device=-1)
 
-# Streamlit UI to upload file
-st.title("Audio Summarization Tool")
-uploaded_file = st.file_uploader("Upload an audio file", type=["wav", "mp3", "flac"])
+# Streamlit file uploader
+uploaded_file = st.file_uploader("Upload an audio file", type=["wav"])
 
+# Process the uploaded file
 if uploaded_file is not None:
-    # Read the audio file with soundfile
-    audio_data, sample_rate = sf.read(uploaded_file)
-
-    # Transcribing audio
-    lecture_text = transcriber(audio_data)["text"]
-
-    # Preprocessing data
+    # Save the uploaded file temporarily
+    audio_data, samplerate = sf.read(uploaded_file)
+    
+    # Transcribing the audio
+    with st.spinner('Transcribing the audio...'):
+        lecture_text = transcriber(uploaded_file)["text"]
+
+    # Preprocessing text
     num_words = len(lecture_text.split())
     max_length = min(num_words, 1024)  # BART model max input length is 1024 tokens
-    max_length = int(max_length * 0.75)  # Convert max words to approx tokens
-
-    if max_length > 1024:
-        lecture_text = lecture_text[:int(1024 / 0.75)]  # Truncate to fit the model's token limit
+    max_length = int(max_length * 0.75)  # Approx token conversion
 
     # Summarization
-    summary = summarizer(
-        lecture_text,
-        max_length=1024,  # DistilBART max input length is 1024 tokens
-        min_length=int(max_length * 0.1),
-        truncation=True
-    )
+    with st.spinner('Summarizing the lecture...'):
+        summary = summarizer(
+            lecture_text,
+            max_length=1024,  # DistilBART max input length
+            min_length=int(max_length * 0.1),
+            truncation=True
+        )
 
     # Clean up the summary text
     if not summary[0]["summary_text"].endswith((".", "!", "?")):
@@ -42,6 +41,9 @@ if uploaded_file is not None:
         if last_period_index != -1:
             summary[0]["summary_text"] = summary[0]["summary_text"][:last_period_index + 1]
 
-    # Output
-    st.write("### Summary:")
-    st.write(summary[0]["summary_text"])
+    # Output summary
+    st.write("\n### Summary:\n", summary[0]["summary_text"])
+
+else:
+    st.warning("Please upload a valid audio file.")
+