Update app.py

app.py

@@ -1,17 +1,25 @@
 import gradio as gr
-from transformers import pipeline
+import openai
 from langdetect import detect
+from transformers import pipeline
+import os
+
+openai.api_key = os.getenv("OPENAI_API_KEY")  # Set this as a secret in your Space settings
 
-asr = pipeline("automatic-speech-recognition", model="openai/whisper-small")
 summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
 
 def process_audio(audio_path):
-    # Accept only valid, non-empty file path (string)
     if not audio_path or not isinstance(audio_path, str):
         return "No audio file provided.", "", "", ""
     try:
-        result = asr(audio_path)
-        transcript = result["text"]
+        # Send audio to OpenAI Whisper API
+        with open(audio_path, "rb") as audio_file:
+            transcript_response = openai.audio.transcriptions.create(
+                model="whisper-1",
+                file=audio_file,
+                response_format="text"
+            )
+        transcript = transcript_response
     except Exception as e:
         return f"Error in transcription: {e}", "", "", ""
     try:
@@ -23,8 +31,14 @@ def process_audio(audio_path):
     transcript_en = transcript
     if detected_lang != "en":
         try:
-            result_translate = asr(audio_path, generate_kwargs={"task": "translate"})
-            transcript_en = result_translate["text"]
+            # Re-send with task=translate for translation to English
+            with open(audio_path, "rb") as audio_file:
+                translation_response = openai.audio.translations.create(
+                    model="whisper-1",
+                    file=audio_file,
+                    response_format="text"
+                )
+            transcript_en = translation_response
         except Exception as e:
             transcript_en = f"Error translating: {e}"
     try:
@@ -43,8 +57,8 @@ iface = gr.Interface(
         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."
+    title="Audio Transcript, Translation & Summary (via OpenAI Whisper API)",
+    description="Upload your audio file (MP3/WAV). This app transcribes via OpenAI Whisper API, detects language, translates to English if needed, and summarizes."
 )
 
 iface.launch()