Trouve Alexis
fa8ea2907b
- Replace cpp-httplib with native WinHTTP for HTTPS support - Switch from whisper-1 to gpt-4o-mini-transcribe model - Use Opus/OGG encoding instead of WAV (~10x smaller files) - Implement sliding window audio capture with overlap - Add transcription deduplication for overlapping segments - Add Voice Activity Detection (VAD) to filter silence/noise - Filter Whisper hallucinations (Amara.org, etc.) - Add UTF-8 console support for Chinese characters - Add Chinese font loading in ImGui - Make Claude responses concise (translation only, no explanations) - Configurable window size, font size, chunk duration/step 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
104 lines
2.9 KiB
C++
104 lines
2.9 KiB
C++
#include <iostream>
|
|
#include <fstream>
|
|
#include <string>
|
|
#include "utils/Config.h"
|
|
#include "core/Pipeline.h"
|
|
|
|
#ifdef _WIN32
|
|
#include <windows.h>
|
|
#endif
|
|
|
|
// Force NVIDIA GPU on Optimus systems (instead of integrated AMD/Intel)
|
|
// These MUST be global and volatile to prevent linker optimization
|
|
#ifdef _WIN32
|
|
extern "C" {
|
|
// NVIDIA Optimus: Force high-performance GPU
|
|
__attribute__((visibility("default")))
|
|
__attribute__((used))
|
|
volatile unsigned long NvOptimusEnablement = 0x00000001;
|
|
|
|
// AMD PowerXpress: Force high-performance GPU
|
|
__attribute__((visibility("default")))
|
|
__attribute__((used))
|
|
volatile int AmdPowerXpressRequestHighPerformance = 1;
|
|
}
|
|
|
|
// Ensure the symbols are referenced so linker doesn't strip them
|
|
static void* __force_gpu_exports[] __attribute__((used)) = {
|
|
(void*)&NvOptimusEnablement,
|
|
(void*)&AmdPowerXpressRequestHighPerformance
|
|
};
|
|
#endif
|
|
|
|
// Simple file logger
|
|
void log_msg(const std::string& msg) {
|
|
std::ofstream log("main_debug.log", std::ios::app);
|
|
log << msg << std::endl;
|
|
log.flush();
|
|
std::cout << msg << std::endl;
|
|
}
|
|
|
|
int main(int argc, char** argv) {
|
|
(void)argc;
|
|
(void)argv;
|
|
|
|
#ifdef _WIN32
|
|
// Enable UTF-8 console output for Chinese characters
|
|
SetConsoleOutputCP(CP_UTF8);
|
|
SetConsoleCP(CP_UTF8);
|
|
#endif
|
|
|
|
log_msg("MAIN: Entry point reached");
|
|
log_msg("========================================");
|
|
log_msg("SecondVoice - Real-time Translation System");
|
|
log_msg("========================================");
|
|
log_msg("Starting application...");
|
|
|
|
// Load configuration
|
|
log_msg("Loading configuration...");
|
|
secondvoice::Config& config = secondvoice::Config::getInstance();
|
|
if (!config.load("config.json", ".env")) {
|
|
log_msg("ERROR: Failed to load configuration");
|
|
return 1;
|
|
}
|
|
|
|
log_msg("Configuration loaded successfully");
|
|
log_msg("");
|
|
|
|
// Create and initialize pipeline
|
|
log_msg("Creating pipeline...");
|
|
secondvoice::Pipeline pipeline;
|
|
log_msg("Initializing pipeline...");
|
|
if (!pipeline.initialize()) {
|
|
log_msg("ERROR: Failed to initialize pipeline");
|
|
return 1;
|
|
}
|
|
|
|
log_msg("Pipeline initialized successfully");
|
|
log_msg("Starting recording and translation...");
|
|
|
|
// Start pipeline (background threads for audio + API calls)
|
|
log_msg("Starting pipeline...");
|
|
if (!pipeline.start()) {
|
|
log_msg("ERROR: Failed to start pipeline");
|
|
return 1;
|
|
}
|
|
|
|
// Main loop - UI runs in main thread (required by GLFW)
|
|
log_msg("Pipeline running, entering main loop...");
|
|
while (pipeline.isRunning() && !pipeline.shouldClose()) {
|
|
pipeline.update(); // Render one frame
|
|
std::this_thread::sleep_for(std::chrono::milliseconds(16)); // ~60 FPS
|
|
}
|
|
|
|
log_msg("");
|
|
log_msg("Recording stopped");
|
|
log_msg("Saving audio...");
|
|
|
|
pipeline.stop();
|
|
|
|
log_msg("Done!");
|
|
|
|
return 0;
|
|
}
|