Update docs for v3 truly self-hosted setup

This commit is contained in:
ifedan-ed 2026-03-31 23:12:46 +00:00
parent 0dc6812f38
commit 39d9a1f9e8

View file

@ -2,28 +2,28 @@
## Overview ## Overview
As of v18, Browser Whisper is **fully self-hosted** with **zero CDN dependencies**. All models and libraries are bundled with the application. As of v3, Browser Whisper is **fully self-hosted** with **zero CDN dependencies**. All models and libraries are bundled with the application and served from your own server.
## What Changed ## What Changed
**Before (v17 and earlier):** **Before (v2 and earlier):**
- Loaded transformers.js from `cdn.jsdelivr.net` - Loaded transformers.js from `cdn.jsdelivr.net`
- Downloaded models from `cdn-lfs.huggingface.co` - Downloaded models from `cdn-lfs.huggingface.co`
- Failed in corporate/clinical networks with firewall restrictions - Failed in corporate/clinical networks with firewall restrictions
**Now (v18+):** **Now (v3+):**
- Transformers.js library bundled at `/models/transformers.min.js` - Transformers.js library (v2.6.2) bundled at `/models/transformers.min.js` (760KB)
- Whisper model bundled at `/models/Xenova/whisper-tiny.en/` - Whisper model bundled at `/models/Xenova/whisper-tiny.en/` (42MB)
- Everything served from your own server - Everything served from your own server
- **Works in any network environment** - **Works in any network environment** (firewalled, air-gapped, offline)
## Files Included ## Files Included
``` ```
public/models/ public/models/
├── transformers.min.js (~876KB) - Transformers.js library ├── transformers.min.js (760KB) - Transformers.js v2.6.2 (worker-compatible)
└── Xenova/ └── Xenova/
└── whisper-tiny.en/ (~42MB total) └── whisper-tiny.en/ (42MB total)
├── config.json ├── config.json
├── tokenizer.json ├── tokenizer.json
├── preprocessor_config.json ├── preprocessor_config.json