e57647c9a3
New cmd/mavwaked — always-on voice listening client that: - Captures PCM from arecord subprocess (16kHz mono int16) - Runs energy-based VAD in 30ms windows (RMS threshold, adaptive floor) - Buffers utterances (300ms min speech, 800ms silence end, 10s max) - Sends complete utterances as PushToTalk with Surface=SurfaceVoice (L0) - Plays reply audio through aplay subprocess - No new CGo/onnxruntime deps — pure Go - 10 VAD tests with -race (speech detect, silence, max duration, reset, adaptive floor) - Makefile build-waked target + Dockerfile integration + alsa-utils runtime dep
104 lines
4.0 KiB
Makefile
104 lines
4.0 KiB
Makefile
GO := $(shell pwd)/deps/go/go/bin/go
|
|
GOFLAGS :=
|
|
CGO_LDFLAGS := -L$(shell pwd)/deps/lib -Wl,-rpath,$(shell pwd)/deps/lib
|
|
CGO_CFLAGS := -I$(shell pwd)/deps/include -I$(shell pwd)/deps/whisper.cpp/ggml/include
|
|
|
|
WHISPER_MODEL := $(shell pwd)/models/stt/ggml-small.bin
|
|
PIPER_BIN := $(shell pwd)/deps/piper/piper
|
|
PIPER_MODEL := $(shell pwd)/models/tts/ru_RU-irina-medium.onnx
|
|
PIPER_ESPEAK := $(shell pwd)/deps/piper/espeak-ng-data
|
|
|
|
.PHONY: all build build-stt build-tts build-daemon build-client build-waked build-web build-poll build-caldav clean test run-stt run-tts run-web download-embedder
|
|
|
|
all: build
|
|
|
|
build: build-stt build-tts build-daemon build-client build-waked build-web build-poll build-caldav
|
|
|
|
build-stt:
|
|
CGO_CFLAGS="$(CGO_CFLAGS)" CGO_LDFLAGS="$(CGO_LDFLAGS)" LD_LIBRARY_PATH="$(shell pwd)/deps/lib" \
|
|
$(GO) build $(GOFLAGS) -o mavsttd ./cmd/mavsttd/
|
|
|
|
build-tts:
|
|
CGO_CFLAGS="$(CGO_CFLAGS)" CGO_LDFLAGS="$(CGO_LDFLAGS)" LD_LIBRARY_PATH="$(shell pwd)/deps/lib" \
|
|
$(GO) build $(GOFLAGS) -o mavttsd ./cmd/mavttsd/
|
|
|
|
build-daemon:
|
|
CGO_CFLAGS="$(CGO_CFLAGS)" CGO_LDFLAGS="$(CGO_LDFLAGS)" LD_LIBRARY_PATH="$(shell pwd)/deps/lib" \
|
|
$(GO) build $(GOFLAGS) -o mavend ./cmd/mavend/
|
|
|
|
build-client:
|
|
CGO_CFLAGS="$(CGO_CFLAGS)" CGO_LDFLAGS="$(CGO_LDFLAGS)" LD_LIBRARY_PATH="$(shell pwd)/deps/lib" \
|
|
$(GO) build $(GOFLAGS) -o mavenclient ./cmd/mavenclient/
|
|
|
|
build-waked:
|
|
$(GO) build $(GOFLAGS) -o mavwaked ./cmd/mavwaked/
|
|
|
|
build-web:
|
|
$(GO) build $(GOFLAGS) -o mavweb ./cmd/mavweb/
|
|
|
|
build-poll:
|
|
$(GO) build $(GOFLAGS) -o mavpoll ./cmd/mavpoll/
|
|
|
|
build-caldav:
|
|
$(GO) build $(GOFLAGS) -o mavcaldav ./cmd/mavcaldav/
|
|
|
|
run-web: build-web
|
|
./mavweb -addr :9200 -voice 127.0.0.1:9100
|
|
|
|
test:
|
|
CGO_CFLAGS="$(CGO_CFLAGS)" CGO_LDFLAGS="$(CGO_LDFLAGS)" LD_LIBRARY_PATH="$(shell pwd)/deps/lib" \
|
|
$(GO) test -race -coverprofile=coverage.out ./internal/... ./cmd/...
|
|
|
|
run-stt: build-stt
|
|
LD_LIBRARY_PATH="$(shell pwd)/deps/lib" \
|
|
./mavsttd -socket /tmp/maven/stt.sock -model $(WHISPER_MODEL)
|
|
|
|
run-tts: build-tts
|
|
LD_LIBRARY_PATH="$(shell pwd)/deps/piper" \
|
|
./mavttsd -socket /tmp/maven/tts.sock \
|
|
-piper $(PIPER_BIN) -model $(PIPER_MODEL) -espeak_data $(PIPER_ESPEAK)
|
|
|
|
deps: deps-whisper deps-piper
|
|
|
|
deps-whisper:
|
|
cd deps/whisper.cpp && cmake -B build -DCMAKE_BUILD_TYPE=Release \
|
|
-DWHISPER_BUILD_TESTS=OFF -DWHISPER_BUILD_SERVER=OFF && \
|
|
cmake --build build --config Release -j$$(nproc)
|
|
cp deps/whisper.cpp/build/bin/libwhisper.so* deps/lib/
|
|
cp deps/whisper.cpp/build/bin/libggml*.so* deps/lib/
|
|
cp deps/whisper.cpp/build/bin/libparakeet.so* deps/lib/
|
|
|
|
deps-piper:
|
|
mkdir -p deps/
|
|
curl -sL "https://github.com/rhasspy/piper/releases/download/2023.11.14-2/piper_linux_x86_64.tar.gz" \
|
|
-o /tmp/piper.tar.gz
|
|
tar -xzf /tmp/piper.tar.gz -C deps/
|
|
|
|
EMBEDDER_DIR := $(shell pwd)/models/embedder
|
|
EMBEDDER_MODEL_URL := https://huggingface.co/Xenova/paraphrase-multilingual-MiniLM-L12-v2/resolve/main/onnx/model_quantized.onnx
|
|
EMBEDDER_TOKENIZER_URL := https://huggingface.co/Xenova/paraphrase-multilingual-MiniLM-L12-v2/resolve/main/tokenizer.json
|
|
|
|
download-embedder:
|
|
mkdir -p $(EMBEDDER_DIR)
|
|
curl -sL "$(EMBEDDER_MODEL_URL)" -o "$(EMBEDDER_DIR)/model_quantized.onnx"
|
|
curl -sL "$(EMBEDDER_TOKENIZER_URL)" -o "$(EMBEDDER_DIR)/tokenizer.json"
|
|
@echo ""
|
|
@echo "embedder model downloaded to $(EMBEDDER_DIR)/"
|
|
@echo "To use it, add to mavend.json:"
|
|
@echo ' "voice": {'
|
|
@echo ' ...'
|
|
@echo ' "embedder": {'
|
|
@echo ' "model_path": "$(EMBEDDER_DIR)/model_quantized.onnx",'
|
|
@echo ' "tokenizer_path": "$(EMBEDDER_DIR)/tokenizer.json",'
|
|
@echo ' "lib_path": "/path/to/libonnxruntime.so"'
|
|
@echo ' }'
|
|
@echo ' }'
|
|
@echo ""
|
|
@echo "Install libonnxruntime.so from: https://github.com/microsoft/onnxruntime/releases"
|
|
@echo "e.g. on x86_64 Linux:"
|
|
@echo ' curl -sL "https://github.com/microsoft/onnxruntime/releases/download/v1.15.1/onnxruntime-linux-x64-1.15.1.tgz" | tar xz'
|
|
@echo ' sudo cp onnxruntime-linux-x64-1.15.1/lib/libonnxruntime.so* /usr/local/lib/'
|
|
|
|
clean:
|
|
rm -f mavend mavenclient mavsttd mavttsd mavweb mavpoll mavcaldav mavwaked
|