https://github.com/hrussellzfac023/voiceworks-toolkit
Japanese language learning toolkit for immersion with native voiceworks. Tampermonkey userscript for asmr.one with on-device Whisper transcription, neural translation, semantic search, and 20+ features — all running locally in-browser.
https://github.com/hrussellzfac023/voiceworks-toolkit
asmr-one dlsite japanese-learning language-learning openvino python pytorch speech-to-text tampermonkey transformers-js typescript userscript webgpu whisper whisper-transcription wxpython
Last synced: 3 months ago
JSON representation
Japanese language learning toolkit for immersion with native voiceworks. Tampermonkey userscript for asmr.one with on-device Whisper transcription, neural translation, semantic search, and 20+ features — all running locally in-browser.
- Host: GitHub
- URL: https://github.com/hrussellzfac023/voiceworks-toolkit
- Owner: HRussellZFAC023
- Created: 2026-01-28T12:28:22.000Z (4 months ago)
- Default Branch: main
- Last Pushed: 2026-02-15T17:12:28.000Z (4 months ago)
- Last Synced: 2026-02-15T23:51:28.323Z (4 months ago)
- Topics: asmr-one, dlsite, japanese-learning, language-learning, openvino, python, pytorch, speech-to-text, tampermonkey, transformers-js, typescript, userscript, webgpu, whisper, whisper-transcription, wxpython
- Language: TypeScript
- Homepage: https://hrussellzfac023.github.io/voiceworks-toolkit/
- Size: 5.68 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Voiceworks Toolkit
Tools for Japanese language learning and library management with native voiceworks from DLsite and [asmr.one](https://as.mr).
## [Voiceworks Ultimate](asmr-one-ultimate/) — Browser Enhancement Suite
Tampermonkey userscript that transforms asmr.one into a full-featured Japanese learning platform. All AI runs locally in the browser.
- **Learner Mode** — Real-time dual-language subtitles (Japanese primary, blurrable English secondary) with speed control
- **Live Transcription** — On-device Whisper speech-to-text (WebGPU-accelerated), turning any audio into study material
- **Neural Translation** — Two local translation models (JA→EN, ZH→EN) in Web Workers with 8ms batch coalescing
- **Semantic Search** — Find voiceworks by meaning using Jina v3 vector embeddings in IndexedDB
- **Radio & Playlist Modes** — Continuous immersion playback with community playlists
- **30+ Features** — Keyboard shortcuts, infinite scroll, audio visualizer, progress tracking, media viewer, and more
## [Voiceworks Renamer](voiceworks-renamer/) — Desktop Library Organizer
Python desktop app for batch-organizing voicework libraries with metadata enrichment, transcription, and playlist generation.
- **Batch Rename** — Folder and file renaming with customizable templates using scraped DLsite metadata
- **Whisper Transcription** — Kotoba-Whisper v2.0 with multi-backend support (CUDA, ROCm, OpenVINO, XPU, CPU)
- **Audio Tagging** — Rich metadata embedding (ID3, Vorbis, Opus) with MusicBee custom tags
- **Translation** — Auto-translate metadata, scripts, and summaries (EN, JA, ZH, KO)
- **Smart Playlists** — Auto-generated M3U playlists by genre, voice actor, and content type
- **Script Import** — Import community transcripts, translate, and export as LRC/TXT