Enha: whisper binary build with cuda

3 files changed, 46 insertions, 15 deletions

diff --git a/Makefile b/Makefile
index 5ea51a2..6f0c7bb 100644
--- a/Makefile
+++ b/Makefile
@@ -21,7 +21,7 @@ build-whisper: ## Build whisper.cpp from source in batteries directory
 		echo "Cloning whisper.cpp repository to batteries directory..."; \
 		git clone https://github.com/ggml-org/whisper.cpp.git batteries/whisper.cpp; \
 	fi
-	cd batteries/whisper.cpp && make build
+	cd batteries/whisper.cpp && cmake -B build -DGGML_CUDA=ON -DWHISPER_SDL2=ON; cmake --build build --config Release -j 8
 	@echo "Whisper binary built successfully!"
 
 download-whisper-model: ## Download Whisper model for STT in batteries directory
@@ -34,22 +34,46 @@ download-whisper-model: ## Download Whisper model for STT in batteries directory
 	@echo "Whisper model downloaded successfully!"
 
 # Docker targets for STT/TTS services (in batteries directory)
-docker-up: ## Start Docker Compose services for STT and TTS from batteries directory
+docker-up: ## Start all Docker Compose services for STT and TTS from batteries directory
 	@echo "Starting Docker services for STT (whisper) and TTS (kokoro)..."
 	@echo "Note: The Whisper model will be downloaded automatically inside the container on first run"
 	docker-compose -f batteries/docker-compose.yml up -d
 	@echo "Docker services started. STT available at http://localhost:8081, TTS available at http://localhost:8880"
 
-docker-down: ## Stop Docker Compose services from batteries directory
+docker-up-whisper: ## Start only the Whisper STT service
+	@echo "Starting Whisper STT service only..."
+	@echo "Note: The Whisper model will be downloaded automatically inside the container on first run"
+	docker-compose -f batteries/docker-compose.yml up -d whisper
+	@echo "Whisper STT service started. Available at http://localhost:8081"
+
+docker-up-kokoro: ## Start only the Kokoro TTS service
+	@echo "Starting Kokoro TTS service only..."
+	docker-compose -f batteries/docker-compose.yml up -d kokoro-tts
+	@echo "Kokoro TTS service started. Available at http://localhost:8880"
+
+docker-down: ## Stop all Docker Compose services from batteries directory
 	@echo "Stopping Docker services..."
 	docker-compose -f batteries/docker-compose.yml down
 	@echo "Docker services stopped"
 
-docker-logs: ## View logs from Docker services in batteries directory
+docker-down-whisper: ## Stop only the Whisper STT service
+	@echo "Stopping Whisper STT service..."
+	docker-compose -f batteries/docker-compose.yml down whisper
+	@echo "Whisper STT service stopped"
+
+docker-down-kokoro: ## Stop only the Kokoro TTS service
+	@echo "Stopping Kokoro TTS service..."
+	docker-compose -f batteries/docker-compose.yml down kokoro-tts
+	@echo "Kokoro TTS service stopped"
+
+docker-logs: ## View logs from all Docker services in batteries directory
 	@echo "Displaying logs from Docker services..."
 	docker-compose -f batteries/docker-compose.yml logs -f
 
-# Convenience target to setup everything
-setup-complete: setup-whisper docker-up
-	@echo "Complete setup finished! STT and TTS services are running."
-	@echo "Note: Docker services will download the Whisper model automatically if not present."
+docker-logs-whisper: ## View logs from Whisper STT service only
+	@echo "Displaying logs from Whisper STT service..."
+	docker-compose -f batteries/docker-compose.yml logs -f whisper
+
+docker-logs-kokoro: ## View logs from Kokoro TTS service only
+	@echo "Displaying logs from Kokoro TTS service..."
+	docker-compose -f batteries/docker-compose.yml logs -f kokoro-tts
diff --git a/README.md b/README.md
index 9891e20..e48c64a 100644
--- a/README.md
+++ b/README.md
@@ -69,7 +69,14 @@ set values as you need them to be.
 For speech-to-text (STT) and text-to-speech (TTS) functionality:
 1. The project uses Whisper.cpp for STT and Kokoro for TTS
 2. Docker Compose automatically downloads the required Whisper model on first run
-3. To start the services: `make docker-up`
-4. To stop the services: `make docker-down`
-5. The STT service runs on http://localhost:8081
-6. The TTS service runs on http://localhost:8880
+3. To start all services: `make docker-up`
+4. To start only STT service: `make docker-up-whisper`
+5. To start only TTS service: `make docker-up-kokoro`
+6. To stop all services: `make docker-down`
+7. To stop only STT service: `make docker-down-whisper`
+8. To stop only TTS service: `make docker-down-kokoro`
+9. To view all service logs: `make docker-logs`
+10. To view only STT service logs: `make docker-logs-whisper`
+11. To view only TTS service logs: `make docker-logs-kokoro`
+12. The STT service runs on http://localhost:8081
+13. The TTS service runs on http://localhost:8880
diff --git a/config.example.toml b/config.example.toml
index 70dc5e3..b8e95cc 100644
--- a/config.example.toml
+++ b/config.example.toml
@@ -26,13 +26,13 @@ RAGDir = "ragimport"
 # extra tts
 TTS_ENABLED = false
 TTS_URL = "http://localhost:8880/v1/audio/speech"
-TTS_SPEED = 1.0
+TTS_SPEED = 1.2
 # extra stt
 STT_ENABLED = false
 STT_TYPE = "WHISPER_SERVER" # WHISPER_SERVER or WHISPER_BINARY
 STT_URL = "http://localhost:8081/inference"
-WhisperBinaryPath = "./batteries/whisper.cpp/whisper-cli"  # Path to whisper binary (for WHISPER_BINARY mode)
-WhisperModelPath = "./batteries/whisper.cpp/ggml-model.bin"  # Path to whisper model file (for WHISPER_BINARY mode)
+WhisperBinaryPath = "./batteries/whisper.cpp/build/bin/whisper-cli" # Path to whisper binary (for WHISPER_BINARY mode)
+WhisperModelPath = "./batteries/whisper.cpp/ggml-large-v3-turbo.bin"  # Path to whisper model file (for WHISPER_BINARY mode)
 STT_LANG = "en"  # Language for speech recognition (for WHISPER_BINARY mode)
 STT_SR = 16000  # Sample rate for audio recording
 DBPATH = "gflt.db"