Update app.py

app.py

@@ -0,0 +1,56 @@
+import streamlit as st
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor, pipeline
+import torch
+import librosa
+
+# Load models
+@st.cache_resource  # Cache the models for faster reloads
+def load_models():
+    processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
+    model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
+    summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+    return processor, model, summarizer
+
+processor, model, summarizer = load_models()
+
+# Function to convert audio to text
+def audio_to_text(audio_path):
+    speech, _ = librosa.load(audio_path, sr=16000)
+    input_values = processor(speech, return_tensors="pt", sampling_rate=16000).input_values
+    with torch.no_grad():
+        logits = model(input_values).logits
+    predicted_ids = torch.argmax(logits, dim=-1)
+    transcription = processor.decode(predicted_ids[0])
+    return transcription
+
+# Function to summarize text
+def summarize_text(text):
+    summary = summarizer(text, max_length=130, min_length=30, do_sample=False)
+    return summary[0]['summary_text']
+
+# Streamlit app
+def main():
+    st.title("Audio Summarization App")
+    st.write("Upload an audio file to get a summary of its content.")
+
+    # File uploader
+    audio_file = st.file_uploader("Upload Audio File", type=["wav", "mp3", "ogg"])
+
+    if audio_file is not None:
+        st.audio(audio_file, format="audio/wav")
+
+        # Process the audio file
+        if st.button("Generate Summary"):
+            with st.spinner("Processing audio..."):
+                # Convert audio to text
+                text = audio_to_text(audio_file)
+                st.subheader("Transcribed Text:")
+                st.write(text)
+
+                # Summarize the text
+                summary = summarize_text(text)
+                st.subheader("Summary:")
+                st.write(summary)
+
+if __name__ == "__main__":
+    main()