workers 1

Dockerfile

@@ -10,4 +10,4 @@ COPY --chown=user ./requirements.txt requirements.txt
 RUN pip install --no-cache-dir --upgrade -r requirements.txt
 
 COPY --chown=user . /app
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "5"]
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -15,7 +15,7 @@ print(device)
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
 # Load the model and processor
-model_id = "WajeehAzeemX/whisper-small-ar2_onnx"
+model_id = "./whisper-small-ar2_onnx"
 model = ORTModelForSpeechSeq2Seq.from_pretrained(
     model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
 )