Skip to content

Removing the dependency on Pyannote for Diarization and VAD #15632

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
tango4j wants to merge 9 commits into
base: main
Choose a base branch
from
+3,957 −360
Open

Removing the dependency on Pyannote for Diarization and VAD #15632

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
28e1e61
Removing the dependency on Pyannote
tango4j Apr 21, 2026
5edd254
Apply isort and black reformatting
tango4j Apr 21, 2026
194221d
Fixed linting and unused variables
tango4j Apr 21, 2026
4a4210a
Resolved conflicts
tango4j Apr 21, 2026
e43f8b3
Apply isort and black reformatting
tango4j Apr 21, 2026
58b8dd8
Removing the accidently added image
tango4j Apr 21, 2026
a5f1dc1
Merge branch 'add_py_md_eval' of github.com:NVIDIA-NeMo/NeMo into add…
tango4j Apr 21, 2026
ee2dfea
Removing the accidently an added tutorial notebook box
tango4j Apr 21, 2026
cf5d74c
Removing data folder for notebook cache
tango4j Apr 21, 2026
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
10 changes: 5 additions & 5 deletions examples/speaker_tasks/diarization/neural_diarizer/e2e_diarize_speech.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,7 +55,7 @@
from nemo.collections.asr.parts.utils.speaker_utils import (
audio_rttm_map,
get_uniqname_from_filepath,
timestamps_to_pyannote_object,
timestamps_to_supervisions,
)
from nemo.collections.asr.parts.utils.transcribe_utils import read_and_maybe_sort_manifest
from nemo.collections.asr.parts.utils.vad_utils import (
Expand Down Expand Up @@ -274,9 +274,9 @@ def convert_pred_mat_to_segments(
bypass_postprocessing (bool, optional): if True, postprocessing will be bypassed. Defaults to False.

Returns:
all_hypothesis (list): list of pyannote objects for each audio file.
all_reference (list): list of pyannote objects for each audio file.
all_uems (list): list of pyannote objects for each audio file.
all_hypothesis (list): list of (uniq_id, list[SupervisionSegment]) per audio file.
all_reference (list): list of (uniq_id, list[SupervisionSegment]) per audio file.
all_uems (list): list of (uniq_id, list[SupervisionSegment]) per audio file.
"""
all_hypothesis, all_reference, all_uems = [], [], []
cfg_vad_params = OmegaConf.structured(postprocessing_cfg)
Expand All @@ -294,7 +294,7 @@ def convert_pred_mat_to_segments(
uniq_id = audio_rttm_values["uniq_id"]
else:
uniq_id = get_uniqname_from_filepath(audio_rttm_values["audio_filepath"])
all_hypothesis, all_reference, all_uems = timestamps_to_pyannote_object(
all_hypothesis, all_reference, all_uems = timestamps_to_supervisions(
speaker_timestamps,
uniq_id,
audio_rttm_values,
Expand Down
3 changes: 0 additions & 3 deletions examples/voice_agent/environment.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -328,9 +328,6 @@ dependencies:
- pulp==3.3.0
- pure-eval==0.2.3
- py-cpuinfo==9.0.0
- pyannote-core==5.0.0
- pyannote-database==5.1.3
- pyannote-metrics==3.2.1
- pyarrow==21.0.0
- pybase64==1.4.2
- pybind11==3.0.1
Expand Down
Loading
Loading