Update app.py

app.py

@@ -7,12 +7,13 @@ from fastapi.responses import HTMLResponse
 # Import your model and VAD libraries.
 from silero_vad import VADIterator, load_silero_vad
 
-from transformers import AutoProcessor, pipeline
+from transformers import AutoProcessor, pipeline, WhisperTokenizerFast
 from optimum.onnxruntime import ORTModelForSpeechSeq2Seq
 
 processor = AutoProcessor.from_pretrained("onnx-community/whisper-tiny.en")
 model = ORTModelForSpeechSeq2Seq.from_pretrained("onnx-community/whisper-tiny.en", subfolder="onnx")
-pipe = pipeline("automatic-speech-recognition", model=model, tokenizer=processor.tokenizer, feature_extractor=processor.feature_extractor)
+tokenizer = WhisperTokenizerFast.from_pretrained("openai/whisper-tiny", language="english")
+pipe = pipeline("automatic-speech-recognition", model=model, tokenizer=tokenizer, feature_extractor=processor.feature_extractor, batch_size=16)
 
 # Constants
 SAMPLING_RATE = 16000