Update app.py

app.py

@@ -21,8 +21,7 @@ pipe = pipeline(
     "automatic-speech-recognition",
     model=model,
     tokenizer=processor.tokenizer,
-    feature_extractor=processor.feature_extractor,
-    generate_kwargs = {"task":"transcribe", "language":"<|ar|>"}
+    feature_extractor=processor.feature_extractor
 )
 
 
@@ -33,15 +32,17 @@ async def transcribe_audio(request: Request):
         audio_data = await request.body()
         # Convert binary data to a file-like object
         audio_file = io.BytesIO(audio_data)
-        # Load the audio file using pydub
-        audio_array, sampling_rate = librosa.load(audio_file, sr=16000)
-        # Process the audio array
-        input_features = processor(audio_array, sampling_rate=sampling_rate, return_tensors="pt").input_features
-        # Generate token ids
-        predicted_ids = model.generate(input_features)
-        # Decode token ids to text
-        transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
+        # # Load the audio file using pydub
+        # audio_array, sampling_rate = librosa.load(audio_file, sr=16000)
+        # # Process the audio array
+        # input_features = processor(audio_array, sampling_rate=sampling_rate, return_tensors="pt").input_features
+        # # Generate token ids
+        # predicted_ids = model.generate(input_features)
+        # # Decode token ids to text
+        # transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
+        transcription = pipe(audio_file,generate_kwargs = {"task":"transcribe", "language":"<|ar|>"})
         # Print the transcription
+        print(transcription)
         print(transcription[0])  # Display the transcriptiontry:
         return {"transcription": transcription[0]}
     except Exception as e: