Functions | |
def | parse_args (parser) |
def | load_and_setup_model (model_name, parser, checkpoint, amp_run, to_cuda=True) |
def | print_stats (measurements_all) |
def | main () |
def test_infer_trt.parse_args | ( | parser | ) |
Parse commandline arguments.
def test_infer_trt.load_and_setup_model | ( | model_name, | |
parser, | |||
checkpoint, | |||
amp_run, | |||
to_cuda = True |
|||
) |
def test_infer_trt.print_stats | ( | measurements_all | ) |
def test_infer_trt.main | ( | ) |
Launches text to speech (inference). Inference is executed on a single GPU.