wehub-resource-sync
ba4be087d5
CICD NeMo / cicd-main-unit-tests (push) Blocked by required conditions
CICD NeMo / cicd-main-speech (push) Blocked by required conditions
CICD NeMo / cicd-test-container-build (push) Blocked by required conditions
CICD NeMo / cicd-import-tests (push) Blocked by required conditions
CICD NeMo / L0_Setup_Test_Data_And_Models (push) Blocked by required conditions
CICD NeMo / Nemo_CICD_Test (push) Blocked by required conditions
CICD NeMo / Coverage (e2e) (push) Blocked by required conditions
CICD NeMo / Coverage (unit-test) (push) Blocked by required conditions
CodeQL / Analyze (python) (push) Waiting to run
Create PR to main with cherry-pick from release / cherry-pick (push) Failing after 0s
CICD NeMo / pre-flight (push) Failing after 0s
CICD NeMo / configure (push) Has been skipped
Build, validate, and release Neural Modules / pre-flight (push) Failing after 1s
CICD NeMo / code-linting (push) Has been skipped
CICD NeMo / cicd-wait-in-queue (push) Waiting to run
Build, validate, and release Neural Modules / release (push) Has been skipped
Build, validate, and release Neural Modules / release-summary (push) Has been cancelled
54 lines
2.0 KiB
Python
54 lines
2.0 KiB
Python
# Copyright (c) 2022, 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 multiprocessing import set_start_method
|
|
|
|
from nemo.collections.asr.data.data_simulation import MultiSpeakerSimulator, RIRMultiSpeakerSimulator
|
|
from nemo.core.config import hydra_runner
|
|
|
|
|
|
"""
|
|
This script creates a synthetic diarization session using the provided audio dataset with ctm files.
|
|
Usage:
|
|
python <NEMO_ROOT>/tools/speech_data_simulator/multispeaker_simulator.py \
|
|
num_workers=10 \
|
|
data_simulator.random_seed=42 \
|
|
data_simulator.manifest_filepath=manifest_with_alignment_file.json \
|
|
data_simulator.outputs.output_dir=./simulated_data \
|
|
data_simulator.outputs.output_filename=sim_spk2_sess20 \
|
|
data_simulator.session_config.num_sessions=1000 \
|
|
data_simulator.session_config.num_speakers=2 \
|
|
data_simulator.session_config.session_length=20 \
|
|
data_simulator.background_noise.add_bg=False \
|
|
data_simulator.background_noise.background_manifest=background_noise.json \
|
|
data_simulator.background_noise.snr=40 \
|
|
|
|
Check out parameters in ./conf/data_simulator.yaml.
|
|
"""
|
|
|
|
|
|
@hydra_runner(config_path="conf", config_name="data_simulator.yaml")
|
|
def main(cfg):
|
|
if cfg.data_simulator.rir_generation.use_rir:
|
|
simulator = RIRMultiSpeakerSimulator(cfg=cfg)
|
|
else:
|
|
simulator = MultiSpeakerSimulator(cfg=cfg)
|
|
|
|
set_start_method('spawn', force=True)
|
|
simulator.generate_sessions()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|