0dc6812f38
FINAL WORKING SOLUTION: Previous attempts failed because: - transformers.js v2.17.2 is ES module-only - Module workers require complex CSP and external imports - importScripts() doesn't work with ES modules Solution: - Use transformers.js v2.6.2 (has worker-compatible UMD build) - Bundle library + models, serve entirely from our server - Classic worker with importScripts() - no CSP issues What's self-hosted: - ✅ transformers.min.js (760KB) - at /models/transformers.min.js - ✅ Whisper models (42MB) - at /models/Xenova/whisper-tiny.en/ Worker loads: 1. importScripts('/models/transformers.min.js') - OUR SERVER 2. Loads models from /models/ - OUR SERVER 3. ZERO external network calls 4. Works in any network (firewalled, air-gapped, etc.) This is the production-ready, truly offline solution.
38 lines
1.8 KiB
Docker
38 lines
1.8 KiB
Docker
FROM node:20-alpine
|
|
|
|
WORKDIR /app
|
|
|
|
# ffmpeg: audio conversion for AWS Transcribe (WebM → PCM)
|
|
# curl: download Whisper models for browser-based transcription
|
|
RUN apk add --no-cache ffmpeg curl
|
|
|
|
COPY package.json ./
|
|
RUN npm install --omit=dev
|
|
|
|
COPY . .
|
|
|
|
RUN mkdir -p /app/data/logs
|
|
|
|
# Download Browser Whisper (COMPLETE self-hosting - zero CDN dependencies)
|
|
# Library + Models all bundled and served from our server
|
|
RUN mkdir -p /app/public/models/Xenova/whisper-tiny.en/onnx && \
|
|
cd /app/public/models && \
|
|
echo "Downloading transformers.js library (worker-compatible build)..." && \
|
|
curl -sL -o transformers.min.js https://cdn.jsdelivr.net/npm/@xenova/transformers@2.6.2/dist/transformers.min.js && \
|
|
cd Xenova/whisper-tiny.en && \
|
|
echo "Downloading Whisper model files..." && \
|
|
curl -sL -o config.json https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/config.json && \
|
|
curl -sL -o tokenizer.json https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/tokenizer.json && \
|
|
curl -sL -o preprocessor_config.json https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/preprocessor_config.json && \
|
|
curl -sL -o generation_config.json https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/generation_config.json && \
|
|
curl -sL -o onnx/encoder_model_quantized.onnx https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/onnx/encoder_model_quantized.onnx && \
|
|
curl -sL -o onnx/decoder_model_merged_quantized.onnx https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/onnx/decoder_model_merged_quantized.onnx && \
|
|
echo "✅ Browser Whisper: 100% self-hosted (library: 760KB, models: 42MB)"
|
|
|
|
EXPOSE 3000
|
|
|
|
HEALTHCHECK --interval=30s --timeout=5s --start-period=20s \
|
|
CMD wget --no-verbose --tries=1 --spider http://localhost:3000/api/health || exit 1
|
|
|
|
CMD ["node", "server.js"]
|
|
|