https://github.com/egorsmkv/marblenet-inference

Inference code for Frame MarbleNet (VAD from NeMo)
https://github.com/egorsmkv/marblenet-inference

marblenet ml nemo nvidia speech vad voice-activity-detection

Last synced: 9 months ago
JSON representation

Inference code for Frame MarbleNet (VAD from NeMo)

• Host: GitHub
• URL: https://github.com/egorsmkv/marblenet-inference
• Owner: egorsmkv
• Created: 2024-12-25T22:13:22.000Z (over 1 year ago)
• Default Branch: master
• Last Pushed: 2025-05-20T22:41:12.000Z (about 1 year ago)
• Last Synced: 2025-05-20T22:44:24.747Z (about 1 year ago)
• Topics: marblenet, ml, nemo, nvidia, speech, vad, voice-activity-detection
• Language: Python
• Homepage:
• Size: 57.6 KB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# MarbleNet inference

[![CI pipeline](https://github.com/egorsmkv/marblenet-inference/actions/workflows/ci.yml/badge.svg)](https://github.com/egorsmkv/marblenet-inference/actions/workflows/ci.yml)

This repo contains workable code to run NeMo's model that does Voice Activity Detection.

## Install

```bash

uv venv --python 3.12

source .venv/bin/activate

uv pip install -r requirements.txt

uv pip install -r requirements-dev.txt

```

## Testing

See the VAD pieces in a file:

```bash

python inference.py

```

## Misc

See the VAD pieces in a file:

```bash

python view_rttm.py rttm_outputs/audio_file.rttm

```