liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
60 lines
14 KiB
XML
60 lines
14 KiB
XML
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 40 780 480" width="780" height="480" style="background:#ffffff">
|
|
<defs><marker id="ah" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto"><polygon points="0 0, 12 4, 0 8" fill="#333333"/></marker><marker id="ah-light" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto"><polygon points="0 0, 12 4, 0 8" fill="#999999"/></marker></defs>
|
|
|
|
<rect x="32" y="58" width="170" height="195" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="117" y="80" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">OpenAI Realtime</text>
|
|
<rect x="42" y="94" width="150" height="24" rx="3" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
|
<text x="117" y="106" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="normal">gpt-realtime</text>
|
|
<text x="117" y="136" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="8" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Server-side VAD + определение реплики</text>
|
|
<text x="117" y="158" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="11" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Асинхронный вызов функции</text>
|
|
<text x="117" y="180" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="7" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Прерывание: остановить текущую генерацию</text>
|
|
<text x="117" y="200" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="8.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">По сути всё ещё в рамках VAD</text>
|
|
<text x="117" y="222" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="10.5" fill="#999999" text-anchor="middle" dominant-baseline="central" font-weight="normal">Превью 2024 на основе GPT-4o</text>
|
|
<rect x="214" y="58" width="170" height="195" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="299" y="80" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Gemini Live</text>
|
|
<rect x="224" y="94" width="150" height="24" rx="3" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
|
<text x="299" y="106" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="normal">Gemini 2.0</text>
|
|
<text x="299" y="136" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="7.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Чувствительность VAD настраивается</text>
|
|
<text x="299" y="158" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="6" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Прерывание сохраняет отправленную информацию</text>
|
|
<text x="299" y="180" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="9.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Оптимизация связности диалога</text>
|
|
<text x="299" y="202" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="10" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Аналогично стратегии OpenAI</text>
|
|
<rect x="396" y="58" width="170" height="195" rx="6" fill="#d0d0d0" stroke="#333333" stroke-width="2"/>
|
|
<text x="481" y="80" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Qwen3-Omni</text>
|
|
<rect x="406" y="94" width="150" height="24" rx="3" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
|
<text x="481" y="106" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="normal">Thinker-Talker MoE</text>
|
|
<text x="481" y="136" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="6.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Думать (понимать) + Выражать (генерировать)</text>
|
|
<text x="481" y="158" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="9.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Мультикодбук кодирование речи</text>
|
|
<text x="481" y="180" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="9.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Задержка первого пакета 234мс</text>
|
|
<text x="481" y="202" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="10.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">22/36 тестов достигают SOTA</text>
|
|
<rect x="578" y="58" width="170" height="195" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="663" y="80" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Step-Audio 2</text>
|
|
<rect x="588" y="94" width="150" height="24" rx="3" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
|
<text x="663" y="106" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="6.5" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="normal">Потенциальное кодирование аудио + RL</text>
|
|
<text x="663" y="136" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="12.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Сквозной речевой токен</text>
|
|
<text x="663" y="158" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="8.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Понимание паралингвистики 83,09%</text>
|
|
<text x="663" y="180" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="8" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">CoT-рассуждение + RAG + инструменты</text>
|
|
<text x="663" y="202" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="8.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Превосходит Qwen2.5-Omni (44.18%)</text>
|
|
<rect x="40" y="273" width="700" height="100" rx="4" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
|
<text x="390" y="295" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="19" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Общее ограничение: всё ещё зависит от определения очерёдности</text>
|
|
<text x="130.9" y="321" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="7.5" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Недостаточное определение конца хода</text>
|
|
<text x="180" y="341" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Пауза ≠ конец речи</text>
|
|
<text x="180" y="357" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Требуется проактивное руководство</text>
|
|
<text x="400.9" y="321" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="15.19" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Примитивная оценка прерывания</text>
|
|
<text x="400" y="341" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Подтверждения ≠ прерывания</text>
|
|
<text x="400" y="357" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Шум распознан как речь</text>
|
|
<text x="620" y="321" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Корневая причина</text>
|
|
<text x="620" y="341" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Только акустические сигналы</text>
|
|
<text x="620" y="357" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Упускает смысл</text>
|
|
<rect x="40" y="388" width="700" height="120" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="390" y="408" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="20" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Сравнение архитектуры ввода/вывода</text>
|
|
<text x="5.6" y="430" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">Традиционный последовательный</text>
|
|
<text x="264.4" y="430" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="11" fill="#666666" text-anchor="start" dominant-baseline="central" font-weight="normal">Аудио→VAD→ASR→Текст→LLM→Текст→TTS→Аудио</text>
|
|
<text x="60" y="445" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">OpenAI/Gemini</text>
|
|
<text x="210" y="445" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="11" fill="#666666" text-anchor="start" dominant-baseline="central" font-weight="normal">Аудио→сквозная модель (встроенный VAD)→Аудио/Текст</text>
|
|
<text x="60" y="460" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">Qwen3-Omni</text>
|
|
<text x="210" y="460" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="11" fill="#666666" text-anchor="start" dominant-baseline="central" font-weight="normal">Аудио/Изображение/Видео→Thinker (MoE)→Talker→Speech Codec</text>
|
|
<text x="60" y="475" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">Step-Audio 2</text>
|
|
<text x="210" y="475" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="11" fill="#666666" text-anchor="start" dominant-baseline="central" font-weight="normal">Необработанное аудио→Латентный кодировщик→LLM+RL→Аудио+текстовые токены</text>
|
|
<text x="43.1" y="491" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">Полнодуплексный Moshi</text>
|
|
<text x="226.9" y="491" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="8.5" fill="#666666" text-anchor="start" dominant-baseline="central" font-weight="normal">Параллельные двойные аудиопотоки + внутренний текстовый поток монолога → VAD/определение реплик не нужно</text>
|
|
</svg> |