https://github.com/wavekat/wavekat-lab
Developer experimentation tools for the WaveKat libraries. Includes vad-lab, a web-based tool for testing and comparing VAD backends side by side.
https://github.com/wavekat/wavekat-lab
audio audio-processing developer-tools rust speech-detection vad voice voice-ai wavekat
Last synced: about 2 months ago
JSON representation
Developer experimentation tools for the WaveKat libraries. Includes vad-lab, a web-based tool for testing and comparing VAD backends side by side.
- Host: GitHub
- URL: https://github.com/wavekat/wavekat-lab
- Owner: wavekat
- License: apache-2.0
- Created: 2026-03-27T07:58:55.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2026-03-28T08:11:51.000Z (3 months ago)
- Last Synced: 2026-03-28T08:41:15.269Z (3 months ago)
- Topics: audio, audio-processing, developer-tools, rust, speech-detection, vad, voice, voice-ai, wavekat
- Language: TypeScript
- Size: 219 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- License: LICENSE
Awesome Lists containing this project
README
[](https://github.com/wavekat/wavekat-lab/actions/workflows/ci.yml)
[](https://github.com/wavekat/wavekat-lab/actions/workflows/release-please.yml)
[](https://deepwiki.com/wavekat/wavekat-lab)
A research repo for the [WaveKat](https://github.com/wavekat) project — interactive tools and Jupyter notebooks for working with audio models (VAD, turn detection, voice datasets, and more).
> [!WARNING]
> Early development. Things may change.
## What's In Here
```
wavekat-lab/
├── tools/
│ ├── audio-lab/ Real-time VAD + Turn Detection + ASR comparison app (Rust + React)
│ └── cv-explorer/ Mozilla Common Voice dataset browser (Cloudflare Workers + React)
├── notebooks/ Jupyter notebooks (training, validation, dataset splits)
└── docs/ Plans and design docs
```
Each tool is self-contained — its own Makefile, lockfiles, and build setup live inside its folder.
## Tools
### [Audio Lab](tools/audio-lab/) — `tools/audio-lab/`
Web app for testing and comparing WaveKat library backends side by side in real time. Live mic capture, WAV upload, multi-config fan-out, VAD-gated pipeline mode, live ASR transcripts, waveform + spectrogram + probability timelines.
Backends: webrtc-vad, silero-vad, ten-vad, firered-vad, pipecat smart-turn, sherpa-onnx ASR. [Details →](tools/audio-lab/README.md)
### [Common Voice Explorer](tools/cv-explorer/) — `tools/cv-explorer/`
Web app for browsing and playing audio clips from the [Mozilla Common Voice](https://commonvoice.mozilla.org) dataset. Filter by locale, split, demographics, and search sentences — with waveform playback powered by WaveSurfer.js. Built on Cloudflare Workers + D1 + R2. [Details →](tools/cv-explorer/README.md)
Live:
## Notebooks
`notebooks/` is the home for Jupyter notebooks covering training, validation, and dataset-splitting workflows. Python env is managed by [uv](https://docs.astral.sh/uv/).
```bash
make setup-notebooks # one-time: uv sync the notebook env
make lab # start Jupyter Lab on notebooks/
```
## Repo Layout Conventions
- **Per-tool Makefiles** — `tools//Makefile` owns dev/build/CI for that tool. Run `cd tools/ && make help` to see what's there.
- **Root Makefile** — repo-wide only: `setup`, `lab`, `ci`, and per-tool CI delegators.
- **No shared Cargo workspace at root** — each Rust tool keeps its own `Cargo.toml` / `Cargo.lock` / `target/` inside its folder.
## Videos
| Video | Description |
|---|---|
| 
| **[Exploring Mozilla Common Voice with Common Voice Explorer](https://www.youtube.com/watch?v=8IScEH0ZJxA)**
Introducing Common Voice Explorer — browse and listen to 1.8M+ real voice clips from the Mozilla Common Voice dataset. |
| 
| **[Testing Pipecat Smart Turn with WaveKat Lab](https://www.youtube.com/watch?v=_dRgH6FZRpM)**
Visual test of Pipecat Smart Turn v3 — live recording and VAD-gated pipeline mode simulating production workflows. |
| 
| **[Adding FireRedVAD as the 4th backend](https://www.youtube.com/watch?v=j2KkhpFRKaY)**
Benchmarking Xiaohongshu's FireRedVAD against Silero, TEN VAD, and WebRTC across accuracy and latency. |
| 
| **[VAD Lab: Real-time multi-backend comparison](https://www.youtube.com/watch?v=450O3w9c-e8)**
Live demo of VAD Lab comparing WebRTC, Silero, and TEN VAD side by side with real-time waveform visualization. |
## License
Licensed under [Apache 2.0](LICENSE).
Copyright 2026 WaveKat.