File size: 2,436 Bytes
7222c68 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 |
import argparse
import os
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument('--port', '-p',
type=int,
default=9090,
help="Websocket port to run the server on.")
parser.add_argument('--backend', '-b',
type=str,
default='faster_whisper',
help='Backends from ["tensorrt", "faster_whisper", "openvino"]')
parser.add_argument('--faster_whisper_custom_model_path', '-fw',
type=str, default=None,
help="Custom Faster Whisper Model")
parser.add_argument('--trt_model_path', '-trt',
type=str,
default=None,
help='Whisper TensorRT model path')
parser.add_argument('--trt_multilingual', '-m',
action="store_true",
help='Boolean only for TensorRT model. True if multilingual.')
parser.add_argument('--trt_py_session',
action="store_true",
help='Boolean only for TensorRT model. Use python session or cpp session, By default uses Cpp.')
parser.add_argument('--omp_num_threads', '-omp',
type=int,
default=1,
help="Number of threads to use for OpenMP")
parser.add_argument('--no_single_model', '-nsm',
action='store_true',
help='Set this if every connection should instantiate its own model. Only relevant for custom model, passed using -trt or -fw.')
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",
port=args.port,
backend=args.backend,
faster_whisper_custom_model_path=args.faster_whisper_custom_model_path,
whisper_tensorrt_path=args.trt_model_path,
trt_multilingual=args.trt_multilingual,
trt_py_session=args.trt_py_session,
single_model=not args.no_single_model,
)
|