Skip to content
New issue

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

#

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

Already on GitHub? # to your account

speaker-identification-with-vad-non-streaming-asr.py Lack of support for sense_voice. #1884

Merged
merged 4 commits into from
Feb 18, 2025
Merged

speaker-identification-with-vad-non-streaming-asr.py Lack of support for sense_voice. #1884

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
bef7495
Fix that speaker-identification-with-vad-non-streaming-asr.py does no…
VisminLab Feb 18, 2025
dc77509
Fix that speaker-identification-with-vad-non-streaming-asr.py does no…
VisminLab Feb 18, 2025
acb5aba
Merge branch 'k2-fsa:master' into master
VisminLab Feb 18, 2025
5b01b6d
Update python-api-examples/speaker-identification-with-vad-non-stream…
VisminLab Feb 18, 2025
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
16 changes: 16 additions & 0 deletions python-api-examples/speaker-identification-with-vad-non-streaming-asr.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -185,6 +185,13 @@ def register_non_streaming_asr_model_args(parser):
help="Feature dimension. Must match the one expected by the model",
)

parser.add_argument(
"--sense-voice",
default="",
type=str,
help="Path to sense voice model",
)


def get_args():
parser = argparse.ArgumentParser(
Expand Down Expand Up @@ -317,6 +324,15 @@ def create_recognizer(args) -> sherpa_onnx.OfflineRecognizer:
task=args.whisper_task,
tail_paddings=args.whisper_tail_paddings,
)
elif args.sense_voice:
assert_file_exists(args.sense_voice)
recognizer = sherpa_onnx.OfflineRecognizer.from_sense_voice(
model=args.sense_voice,
tokens=args.tokens,
num_threads=args.num_threads,
use_itn=True,
debug=args.debug,
)
else:
raise ValueError("Please specify at least one model")

Expand Down