Thanks to visit codestin.com
Credit goes to github.com

Skip to content

added parser argument to support MPS by default #1501

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
NripeshN wants to merge 6 commits into
base: main
Choose a base branch
from
Open

added parser argument to support MPS by default #1501

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
e0f0221
added parser argument to support MPS by default
NripeshN Jul 5, 2023
7c198b0
Merge branch 'main' into transcribe-argument
NripeshN Sep 29, 2023
de98888
Merge branch 'main' into transcribe-argument
NripeshN Oct 23, 2023
8445f2a
Merge branch 'main' into transcribe-argument
NripeshN Dec 10, 2023
c2d3099
Merge branch 'main' into transcribe-argument
NripeshN May 28, 2024
888dd61
Merge branch 'main' into transcribe-argument
NripeshN Dec 4, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 8 additions & 1 deletion whisper/transcribe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -517,6 +517,13 @@ def next_words_segment(segments: List[dict]) -> Optional[dict]:
def cli():
from . import available_models

if torch.cuda.is_available():
default_device = "cuda"
elif hasattr(torch.backends, 'mps') and torch.backends.mps.is_available():
default_device = "mps"
else:
default_device = "cpu"

def valid_model_name(name):
if name in available_models() or os.path.exists(name):
return name
Expand All @@ -529,7 +536,7 @@ def valid_model_name(name):
parser.add_argument("audio", nargs="+", type=str, help="audio file(s) to transcribe")
parser.add_argument("--model", default="turbo", type=valid_model_name, help="name of the Whisper model to use")
parser.add_argument("--model_dir", type=str, default=None, help="the path to save model files; uses ~/.cache/whisper by default")
parser.add_argument("--device", default="cuda" if torch.cuda.is_available() else "cpu", help="device to use for PyTorch inference")
parser.add_argument("--device", default=default_device, help="device to use for PyTorch inference")
parser.add_argument("--output_dir", "-o", type=str, default=".", help="directory to save the outputs")
parser.add_argument("--output_format", "-f", type=str, default="all", choices=["txt", "vtt", "srt", "tsv", "json", "all"], help="format of the output file; if not specified, all available formats will be produced")
parser.add_argument("--verbose", type=str2bool, default=True, help="whether to print out the progress and debug messages")
Expand Down