Skip to content

rename folder VAD -> vad #4163

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

Merged
fayejf merged 6 commits into from
May 16, 2022
Merged

rename folder VAD -> vad #4163

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
723364f
rename folder VAD->vad
fayejf May 12, 2022
33a1681
Merge branch 'r1.9.0' into lowercase_vad_folder_name
fayejf May 12, 2022
80795ac
Merge branch 'r1.9.0' into lowercase_vad_folder_name
fayejf May 13, 2022
d5df001
Merge branch 'r1.9.0' into lowercase_vad_folder_name
fayejf May 14, 2022
a3e368b
Merge branch 'r1.9.0' into lowercase_vad_folder_name
fayejf May 16, 2022
8d0fde4
Merge branch 'r1.9.0' into lowercase_vad_folder_name
fayejf May 16, 2022
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
4 changes: 2 additions & 2 deletions docs/source/asr/speech_classification/results.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,12 +51,12 @@ Learn how to fine tune on your own data or on subset classes in ``<NeMo_git_root

.. code-block:: bash

python <NeMo-git-root>/examples/asr/speech_classification/vad_infer.py --config-path="../conf/VAD" --config-name="vad_inference_postprocessing.yaml" dataset=<Path of json file of evaluation data. Audio files should have unique names>
python <NeMo-git-root>/examples/asr/speech_classification/vad_infer.py --config-path="../conf/vad" --config-name="vad_inference_postprocessing.yaml" dataset=<Path of json file of evaluation data. Audio files should have unique names>


This script will perform vad frame-level prediction and will help you perform postprocessing and generate speech segments as well if needed.

Have a look at configuration file ``<NeMo-git-root>/examples/asr/conf/VAD/vad_inference_postprocessing.yaml`` and scripts under ``<NeMo-git-root>/scripts/voice_activity_detection`` for details regarding posterior processing, postprocessing and threshold tuning.
Have a look at configuration file ``<NeMo-git-root>/examples/asr/conf/vad/vad_inference_postprocessing.yaml`` and scripts under ``<NeMo-git-root>/scripts/voice_activity_detection`` for details regarding posterior processing, postprocessing and threshold tuning.

Posterior processing includes generating predictions with overlapping input segments. Then a smoothing filter is applied to decide the label for a frame spanned by multiple segments.

Expand Down
0 ...onf/VAD/vad_inference_postprocessing.yaml → ...onf/vad/vad_inference_postprocessing.yaml
View file
Open in desktop
File renamed without changes.
4 changes: 2 additions & 2 deletions examples/asr/speech_classification/vad_infer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@
This script will also help you perform postprocessing and generate speech segments if needed

Usage:
python vad_infer.py --config-path="../conf/VAD" --config-name="vad_inference_postprocessing.yaml" dataset=<Path of json file of evaluation data. Audio files should have unique names>
python vad_infer.py --config-path="../conf/vad" --config-name="vad_inference_postprocessing.yaml" dataset=<Path of json file of evaluation data. Audio files should have unique names>

"""
import json
Expand All @@ -49,7 +49,7 @@
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")


@hydra_runner(config_path="../conf/VAD", config_name="vad_inference_postprocessing.yaml")
@hydra_runner(config_path="../conf/vad", config_name="vad_inference_postprocessing.yaml")
def main(cfg):
if not cfg.dataset:
raise ValueError("You must input the path of json file of evaluation data")
Expand Down
8 changes: 4 additions & 4 deletions tutorials/asr/Offline_ASR_with_VAD_for_CTC_models.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,9 +123,9 @@
"if not os.path.exists(\"scripts/transcribe_speech.py\"):\n",
" !wget -P scripts/ https://raw.githubusercontent.com/NVIDIA/NeMo/main/examples/asr/transcribe_speech.py\n",
" \n",
"!mkdir -p conf/VAD\n",
"if not os.path.exists(\"conf/VAD/vad_inference_postprocessing.yaml\"):\n",
" !wget -P conf/VAD/ https://raw.githubusercontent.com/NVIDIA/NeMo/main/examples/asr/conf/VAD/vad_inference_postprocessing.yaml"
"!mkdir -p conf/vad\n",
"if not os.path.exists(\"conf/vad/vad_inference_postprocessing.yaml\"):\n",
" !wget -P conf/vad/ https://raw.githubusercontent.com/NVIDIA/NeMo/main/examples/asr/conf/vad/vad_inference_postprocessing.yaml"
]
},
{
Expand Down Expand Up @@ -166,7 +166,7 @@
"outputs": [],
"source": [
"# if run locally, vad_infer.py is located in <NeMo_git_root>/examples/asr/speech_classification/vad_infer.py\n",
"%run -i scripts/vad_infer.py --config-path=\"../conf/VAD\" --config-name=\"vad_inference_postprocessing.yaml\" \\\n",
"%run -i scripts/vad_infer.py --config-path=\"../conf/vad\" --config-name=\"vad_inference_postprocessing.yaml\" \\\n",
"dataset=$input_manifest \\\n",
"vad.model_path=$vad_model \\\n",
"frame_out_dir=\"chris_demo\" \\\n",
Expand Down
2 changes: 1 addition & 1 deletion tutorials/asr/Online_Offline_Microphone_VAD_Demo.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -202,7 +202,7 @@
"You can find all necessary steps about inference in \n",
"```python\n",
" Script: <NeMo_git_root>/examples/asr/speech_classification/vad_infer.py \n",
" Config: <NeMo_git_root>/examples/asr/conf/VAD/vad_inference_postprocessing.yaml\n",
" Config: <NeMo_git_root>/examples/asr/conf/vad/vad_inference_postprocessing.yaml\n",
"```\n",
"Duration inference, we generate frame-level prediction by two approaches:\n",
"\n",
Expand Down