Update app.py

app.py

@@ -1,52 +1,23 @@
-import whisper
 import gradio as gr
-import time
-from wordcloud import WordCloud
-import matplotlib.pyplot as plt
-import io
-import base64
+import whisper
 
 # Load the Whisper model
 model = whisper.load_model("base")
 
-# Function to transcribe audio and generate a word cloud
-def transcribe_and_generate_wordcloud(audio):
+def transcribe(audio):
     # Transcribe the audio file
-    result = model.transcribe(audio) # Changed audio.name to audio
-    
-    # Split the transcription into sentences
-    text = result["text"]
-    sentences = text.split(". ")
-    
-    # Generate a word cloud
-    wordcloud = WordCloud(width=800, height=400, background_color='white').generate(text)
-    
-    # Save the word cloud image to a BytesIO object
-    buffer = io.BytesIO()
-    plt.figure(figsize=(10, 5))
-    plt.imshow(wordcloud, interpolation='bilinear')
-    plt.axis('off')
-    plt.savefig(buffer, format='png')
-    plt.close()
-    buffer.seek(0)
-    
-    # Encode the image as a base64 string
-    img_str = base64.b64encode(buffer.getvalue()).decode()
-    
-    # Create a delay for demonstration
-    output = "\n".join([s.strip() + "." for s in sentences if s.strip()])
-    time.sleep(2)  # Add a short delay before processing the next part
-    
-    return output, f"data:image/png;base64,{img_str}"
+    result = model.transcribe(audio)
+    return result['text']
 
-# Gradio interface
-interface = gr.Interface(
-    fn=transcribe_and_generate_wordcloud, 
-    inputs=gr.Audio(type="filepath"),  # Change type to "filepath"
-    outputs=[gr.Textbox(label="Transcribed Text"), gr.Image(label="Word Cloud")],
-    title="Local Language Transcription and Word Cloud Generator",
-    description="Upload an audio file in a local language to transcribe it and visualize the text as a word cloud."
+# Create the Gradio interface
+# Removed the 'source' parameter and set type to 'upload' for file uploads. 
+demo = gr.Interface(
+    fn=transcribe,
+    inputs=gr.Audio(type="filepath"),  
+    outputs="text",
+    title="Audio Transcription App",
+    description="Upload an audio file or record your voice to transcribe it to text."
 )
 
-# Launch the Gradio app
-interface.launch()
+# Launch the app
+demo.launch()