blumia
bd921b1ac5
Add a second backend (sherpa-onnx) alongside llama.cpp, so native streaming models can be selected by ID from a JSON registry. All such models share one adapter: only the model files and a few options differ. Models now live under the app data directory and are fetched by scripts/fetch-models.sh. Adding a model is a data change, not code. Measured on the same audio: the streaming backend is ~35x cheaper in CPU than Qwen3-ASR (0.10-0.12 vs 4.27 core-seconds per audio second), shows the first caption at 0.48-1.44s, and matches its accuracy for zh/en. 新增 sherpa-onnx 流式后端，与 llama.cpp 并存；模型按注册表 id 从应用 数据目录加载。同族模型共用一个适配器，新增模型只改 data/models.json。 实测流式后端 CPU 约为 Qwen3-ASR 的 1/35，首个字幕 0.48~1.44s，中英 准确率持平。注意预编译库是旧 C++ ABI，必须走其 C API。
112 lines
4.1 KiB
C++
112 lines
4.1 KiB
C++
// 图形界面版：悬浮字幕窗。
|
||
#include <cstdio>
|
||
|
||
#include <QApplication>
|
||
#include <QCommandLineOption>
|
||
#include <QCommandLineParser>
|
||
#include <QGuiApplication>
|
||
#include <QTimer>
|
||
|
||
#include "appcli.h"
|
||
#include "captionwindow.h"
|
||
#include "livetranscriber.h"
|
||
#include "iasr.h"
|
||
#include "qwen3asr.h"
|
||
#include "streamingasr.h"
|
||
#include "transcript.h"
|
||
|
||
namespace {
|
||
|
||
int runGui(lc::IAsr & asr, const lc::StreamOptions & sop,
|
||
const QString & screenshotPath, int screenshotDelaySec, int opacityPercent)
|
||
{
|
||
lc::CaptionWindow window;
|
||
window.setPanelOpacity(opacityPercent);
|
||
lc::LiveTranscriber live(asr);
|
||
|
||
QObject::connect(&live, &lc::LiveTranscriber::caption, &window,
|
||
[&window](const QString & committed, const QString & tail,
|
||
const QString & lang) {
|
||
window.setLanguage(
|
||
QString::fromStdString(lc::languageDisplayName(lang.toStdString())));
|
||
window.setCaption(committed, tail);
|
||
});
|
||
QObject::connect(&live, &lc::LiveTranscriber::failed, &window, [](const QString & m) {
|
||
qWarning("采集失败: %s", qUtf8Printable(m));
|
||
});
|
||
QObject::connect(&window, &lc::CaptionWindow::closed, qApp, &QCoreApplication::quit);
|
||
QObject::connect(&window, &lc::CaptionWindow::languageClicked, &window, [] {
|
||
qInfo() << "语言标签被点击（设置界面将在 Phase 4 接入）";
|
||
});
|
||
|
||
QString err;
|
||
if (!live.start(sop, &err)) {
|
||
qCritical("启动采集失败: %s", qUtf8Printable(err));
|
||
return 1;
|
||
}
|
||
qInfo("正在采集: %s", qUtf8Printable(live.deviceName()));
|
||
|
||
window.show();
|
||
|
||
if (!screenshotPath.isEmpty()) {
|
||
// 自截图：用于验证渲染（不依赖外部截图工具）
|
||
QTimer::singleShot(screenshotDelaySec * 1000, &window, [&window, screenshotPath] {
|
||
const bool ok1 = window.grab().save(screenshotPath);
|
||
|
||
window.setCollapsed(false);
|
||
QString expandedPath = screenshotPath;
|
||
expandedPath.replace(QStringLiteral(".png"), QStringLiteral("-expanded.png"));
|
||
const bool ok2 = window.grab().save(expandedPath);
|
||
|
||
std::fprintf(stderr, "截图: 折叠态 %s / 展开态 %s\n",
|
||
ok1 ? "成功" : "失败", ok2 ? "成功" : "失败");
|
||
QCoreApplication::quit();
|
||
});
|
||
}
|
||
|
||
return QCoreApplication::exec();
|
||
}
|
||
|
||
} // namespace
|
||
|
||
int main(int argc, char ** argv)
|
||
{
|
||
// 说明意图：DPI 取整策略必须在 QGuiApplication 之前定。
|
||
// （Deepin 的会话环境已经设了 QT_SCALE_FACTOR_ROUNDING_POLICY，
|
||
// 所以本机仍会看到 Qt 的那条提醒，那不是本程序的问题。）
|
||
QGuiApplication::setHighDpiScaleFactorRoundingPolicy(
|
||
Qt::HighDpiScaleFactorRoundingPolicy::PassThrough);
|
||
|
||
QApplication app(argc, argv);
|
||
QCoreApplication::setApplicationName(QStringLiteral("live-caption"));
|
||
|
||
QCommandLineParser parser;
|
||
parser.setApplicationDescription(QStringLiteral("实时字幕（悬浮窗）"));
|
||
parser.addHelpOption();
|
||
lc::app::addModelOptions(parser);
|
||
lc::app::addStreamOptions(parser);
|
||
lc::app::addBackendOptions(parser);
|
||
parser.addOption(lc::app::makeOption("opacity", "字幕背景不透明度，取值 20-100", "n", "84"));
|
||
parser.addOption(lc::app::makeOption("screenshot", "启动后自动截图并退出（验证渲染用）", "path"));
|
||
parser.addOption(lc::app::makeOption("screenshot-delay", "截图前等待秒数", "sec", "6"));
|
||
parser.process(app);
|
||
|
||
const lc::AsrOptions asrOpt = lc::app::asrOptions(parser);
|
||
lc::StreamOptions sop = lc::app::streamOptions(parser);
|
||
|
||
std::string err;
|
||
std::unique_ptr<lc::IAsr> asr = lc::app::makeAsr(parser, asrOpt, &err);
|
||
if (!asr) {
|
||
std::fprintf(stderr, "%s\n", err.c_str());
|
||
return 1;
|
||
}
|
||
if (asr->kind() == lc::AsrKind::NativeStreaming && !parser.isSet("stream-chunk")) {
|
||
sop.chunkSec = 0.32;
|
||
}
|
||
|
||
return runGui(*asr, sop,
|
||
parser.value("screenshot"),
|
||
parser.value("screenshot-delay").toInt(),
|
||
parser.value("opacity").toInt());
|
||
}
|