Merge pull request #215 from makaveli10/fix/omp-num-threads

fix: limit CPU usage for VAD onnxruntime inference session by setting…

README.md

@@ -53,7 +53,13 @@ python3 run_server.py -p 9090 \
                       -trt /home/TensorRT-LLM/examples/whisper/whisper_small \
                       -m
 ```
-
+#### Controlling OpenMP Threads
+To control the number of threads used by OpenMP, you can set the `OMP_NUM_THREADS` environment variable. This is useful for managing CPU resources and ensuring consistent performance. If not specified, `OMP_NUM_THREADS` is set to `1` by default. You can change this by using the `--omp_num_threads` argument:
+```bash
+python3 run_server.py --port 9090 \
+                      --backend faster_whisper \
+                      --omp_num_threads 4
+```
 
 ### Running the Client
 - Initializing the client:

run_server.py

@@ -1,5 +1,5 @@
 import argparse
-from whisper_live.server import TranscriptionServer
+import os
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
@@ -21,12 +21,20 @@
     parser.add_argument('--trt_multilingual', '-m',
                         action="store_true",
                         help='Boolean only for TensorRT model. True if multilingual.')
+    parser.add_argument('--omp_num_threads', '-omp',
+                        type=int,
+                        default=1,
+                        help="Number of threads to use for OpenMP")
     args = parser.parse_args()
 
     if args.backend == "tensorrt":
         if args.trt_model_path is None:
             raise ValueError("Please Provide a valid tensorrt model path")
 
+    if "OMP_NUM_THREADS" not in os.environ:
+        os.environ["OMP_NUM_THREADS"] = str(args.omp_num_threads)
+
+    from whisper_live.server import TranscriptionServer
     server = TranscriptionServer()
     server.run(
         "0.0.0.0",