Add local Whisper speech recognition

2026-09-03 21:59:37 +02:00
parent f1fdca3efd
commit 42ec28c9f6
7 changed files with 189 additions and 1 deletions
@@ -0,0 +1,35 @@
+FROM python:3.13.7-slim-bookworm
+
+ARG WHISPER_CPP_VERSION=v1.9.1
+
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends \
+       build-essential ca-certificates cmake curl ffmpeg git gosu \
+    && git clone --branch "${WHISPER_CPP_VERSION}" --depth 1 \
+       https://github.com/ggml-org/whisper.cpp.git /opt/whisper.cpp \
+    && cmake -S /opt/whisper.cpp -B /opt/whisper.cpp/build \
+       -DCMAKE_BUILD_TYPE=Release \
+       -DGGML_NATIVE=ON \
+       -DWHISPER_BUILD_TESTS=OFF \
+       -DWHISPER_BUILD_SERVER=OFF \
+    && cmake --build /opt/whisper.cpp/build --config Release -j"$(nproc)" \
+    && apt-get purge -y --auto-remove build-essential cmake git \
+    && rm -rf /var/lib/apt/lists/* /root/.cache \
+    && useradd --system --uid 10004 --home-dir /nonexistent --shell /usr/sbin/nologin whisper
+
+WORKDIR /app
+COPY router/stt_worker.py /app/stt_worker.py
+COPY platform/docker/whisper/entrypoint.sh /usr/local/bin/mike-ai-whisper-entrypoint
+RUN chmod 0755 /usr/local/bin/mike-ai-whisper-entrypoint
+
+ENV WHISPER_HOST=0.0.0.0 \
+    WHISPER_PORT=8084 \
+    WHISPER_CLI=/opt/whisper.cpp/build/bin/whisper-cli \
+    WHISPER_MODEL=/models/ggml-large-v3-turbo.bin \
+    WHISPER_THREADS=8 \
+    WHISPER_LANGUAGE=de \
+    FFMPEG_BIN=/usr/bin/ffmpeg
+
+VOLUME ["/models"]
+EXPOSE 8084
+ENTRYPOINT ["/usr/local/bin/mike-ai-whisper-entrypoint"]
@@ -0,0 +1,25 @@
+#!/bin/sh
+set -eu
+
+model=${WHISPER_MODEL:-/models/ggml-large-v3-turbo.bin}
+model_url=${WHISPER_MODEL_URL:-https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-large-v3-turbo.bin}
+model_dir=$(dirname "$model")
+
+mkdir -p "$model_dir"
+chown 10004:10004 "$model_dir"
+
+if [ ! -s "$model" ]; then
+  partial="${model}.part"
+  echo "Downloading Whisper model to persistent storage"
+  # All writes below must use the volume owner. The container deliberately
+  # drops CAP_DAC_OVERRIDE, so even uid 0 cannot rename a file in the
+  # whisper-owned directory after capabilities have been removed.
+  if [ ! -s "$partial" ]; then
+    gosu whisper rm -f "$partial"
+    gosu whisper curl --fail --location --retry 5 --retry-delay 5 \
+      --output "$partial" "$model_url"
+  fi
+  gosu whisper mv "$partial" "$model"
+fi
+
+exec gosu whisper python /app/stt_worker.py