Update app.py

app.py

@@ -1,78 +1,36 @@
 import gradio as gr
 import whisper
-from transformers import pipeline
-import numpy as np
+import os
 
 # Load Whisper model
-whisper_model = whisper.load_model("base")
+model = whisper.load_model("base")
 
-# Load traditional summarization models
-def get_summarizer(model_name):
-    if model_name == "BART (facebook/bart-large-cnn)":
-        return pipeline("summarization", model="facebook/bart-large-cnn")
-    elif model_name == "T5 (t5-small)":
-        return pipeline("summarization", model="t5-small")
-    elif model_name == "Pegasus (google/pegasus-xsum)":
-        return pipeline("summarization", model="google/pegasus-xsum")
-    else:
-        return None
-
-# Function to transcribe raw audio data using Whisper
-def transcribe_audio(model_size, audio):
-    if audio is None:
+# Function to transcribe audio file using Whisper
+def transcribe_audio(audio_file):
+    # Check if the audio file exists and print the file path for debugging
+    if audio_file is None:
         return "No audio file provided."
     
-    # Convert the input audio (which is a tuple) into the format Whisper expects
-    audio_data = np.array(audio[1])  # audio[1] is the raw audio data
-    sample_rate = 16000  # Whisper expects a sample rate of 16kHz
-
-    # Load the selected Whisper model
-    model = whisper.load_model(model_size)
+    # Debugging: Print the file path to check if Gradio passes the file path correctly
+    print(f"Audio file path: {audio_file}")
+    
+    if not os.path.exists(audio_file):
+        return "The audio file does not exist or is inaccessible."
 
-    # Transcribe the audio file
-    result = model.transcribe(audio_data)
+    # Load and transcribe the audio file
+    result = model.transcribe(audio_file)
     transcription = result['text']
     
     return transcription
 
-# Function to summarize the transcribed text
-def summarize_text(transcription, model_name):
-    if len(transcription.strip()) == 0:
-        return "No text to summarize."
-    
-    summarizer = get_summarizer(model_name)
-    
-    if summarizer:
-        summary = summarizer(transcription, max_length=150, min_length=30, do_sample=False)[0]['summary_text']
-        return summary
-    else:
-        return "Invalid summarization model selected."
-
-# Create a Gradio interface that combines transcription and summarization
-def combined_transcription_and_summarization(model_size, summarizer_model, audio):
-    # Step 1: Transcribe the audio using Whisper
-    transcription = transcribe_audio(model_size, audio)
-    
-    # Step 2: Summarize the transcribed text using the chosen summarizer model
-    summary = summarize_text(transcription, summarizer_model)
-    
-    return transcription, summary
-
-# Gradio interface for transcription and summarization
+# Gradio interface for transcription
 iface = gr.Interface(
-    fn=combined_transcription_and_summarization,   # The combined function
-    inputs=[
-        gr.Dropdown(label="Choose Whisper Model", choices=["tiny", "base", "small", "medium", "large"], value="base"),  # Whisper model selection
-        gr.Dropdown(label="Choose Summarizer Model", choices=["BART (facebook/bart-large-cnn)", "T5 (t5-small)", "Pegasus (google/pegasus-xsum)"], value="BART (facebook/bart-large-cnn)"),  # Summarizer model selection
-        gr.Audio(type="numpy")  # This will pass raw audio data as a numpy array
-    ],
-    outputs=[
-        gr.Textbox(label="Transcription"),         # Output for the transcribed text
-        gr.Textbox(label="Summary")                # Output for the summary
-    ],
-    title="Whisper Audio Transcription and Summarization",
-    description="Upload an audio file, choose a Whisper model for transcription, and a summarization model to summarize the transcription."
+    fn=transcribe_audio,   # Function to process audio file
+    inputs=gr.Audio(type="filepath"),  # Audio upload, pass file path
+    outputs="text",       # Output the transcription as text
+    title="Whisper Audio Transcription",
+    description="Upload an audio file and get the transcription."
 )
 
-# Launch the interface
-iface.launch()
+# Launch the Gradio interface with a shareable link (required for Colab)
+iface.launch(share=True)