Update app.py

app.py

@@ -2,19 +2,13 @@ import gradio as gr
 from transformers import pipeline
 from langdetect import detect
 
-# Use the small model for Spaces to avoid OOM
-WHISPER_MODEL = "openai/whisper-small"
-SUMMARIZER_MODEL = "facebook/bart-large-cnn"
-
-# Load pipelines ONCE at startup
-asr = pipeline("automatic-speech-recognition", model=WHISPER_MODEL)
-summarizer = pipeline("summarization", model=SUMMARIZER_MODEL)
+asr = pipeline("automatic-speech-recognition", model="openai/whisper-small")
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
 
 def process_audio(audio_path):
-    if not audio_path or not isinstance(audio_path, str):
+    if not audio_path or isinstance(audio_path, bool):
         return "No audio file provided.", "", "", ""
     try:
-        # Transcription
         result = asr(audio_path)
         transcript = result["text"]
     except Exception as e:
@@ -28,7 +22,6 @@ def process_audio(audio_path):
     transcript_en = transcript
     if detected_lang != "en":
         try:
-            # Use the same pipeline, but set task as "translate" for Whisper
             result_translate = asr(audio_path, generate_kwargs={"task": "translate"})
             transcript_en = result_translate["text"]
         except Exception as e:
@@ -40,18 +33,17 @@ def process_audio(audio_path):
         summary_text = f"Error summarizing: {e}"
     return lang_text, transcript, transcript_en, summary_text
 
-with gr.Blocks() as demo:
-    gr.Markdown("## Audio Transcript, Translation & Summary (Whisper + Hugging Face)")
-    audio_input = gr.Audio(type="filepath", label="Upload MP3/WAV Audio")
-    btn = gr.Button("Process")
-    lang_out = gr.Textbox(label="Detected Language")
-    transcript_out = gr.Textbox(label="Original Transcript")
-    transcript_en_out = gr.Textbox(label="English Transcript (if translated)")
-    summary_out = gr.Textbox(label="Summary")
-    btn.click(
-        process_audio,
-        inputs=[audio_input],
-        outputs=[lang_out, transcript_out, transcript_en_out, summary_out]
-    )
+iface = gr.Interface(
+    fn=process_audio,
+    inputs=gr.Audio(source="upload", type="filepath", label="Upload MP3/WAV Audio"),
+    outputs=[
+        gr.Textbox(label="Detected Language"),
+        gr.Textbox(label="Original Transcript"),
+        gr.Textbox(label="English Transcript (if translated)"),
+        gr.Textbox(label="Summary"),
+    ],
+    title="Audio Transcript, Translation & Summary",
+    description="Upload your audio file (MP3/WAV). This app transcribes, detects language, translates to English if needed, and summarizes."
+)
 
-demo.launch()
+iface.launch()