File size: 1,714 Bytes
7934b29 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 |
# Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from omegaconf import OmegaConf
from pytorch_lightning import seed_everything
from nemo.collections.asr.models import ClusteringDiarizer
from nemo.core.config import hydra_runner
from nemo.utils import logging
"""
This script demonstrates how to use run speaker diarization.
Usage:
python offline_diar_infer.py \
diarizer.manifest_filepath=<path to manifest file> \
diarizer.out_dir='demo_output' \
diarizer.speaker_embeddings.model_path=<pretrained modelname or path to .nemo> \
diarizer.vad.model_path='vad_marblenet' \
diarizer.speaker_embeddings.parameters.save_embeddings=False
Check out whole parameters in ./conf/offline_diarization.yaml and their meanings.
For details, have a look at <NeMo_git_root>/tutorials/speaker_tasks/Speaker_Diarization_Inference.ipynb
"""
seed_everything(42)
@hydra_runner(config_path="../conf/inference", config_name="diar_infer_meeting.yaml")
def main(cfg):
logging.info(f'Hydra config: {OmegaConf.to_yaml(cfg)}')
sd_model = ClusteringDiarizer(cfg=cfg).to(cfg.device)
sd_model.diarize()
if __name__ == '__main__':
main()
|