-
Notifications
You must be signed in to change notification settings - Fork 796
Timestamps in parakeet_runner
#16545
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.
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
base: main
Are you sure you want to change the base?
Timestamps in parakeet_runner
#16545
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16545
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 831f714 with merge base 9ba1b5d ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This PR needs a
|
Summary
Enable computation of timestamps within
parakeet_runnerthrough a--timestampsflag (none|token|word|segment|all). Followed reference implementation from NVIDIA-NeMo/NeMo, which is cited as the way to run parakeet and compute timestamps for nvidia/parakeet-tdt-0.6b-v3 on HF.Requires meta-pytorch/tokenizers#163 for the
id_to_piecemethod onTokenizers.Test plan
Outputs the exact same transcription/timestamps as NVIDIA-NeMo/NeMo for audio files basketball.wav and audio.wav
NeMo (basketball.wav)
Click to see output
parakeet_runner(basketball.wav)Click to see output