docs: refresh docs to match the current state, add GUI/CLI/troubleshooting

The README still listed the settings UI as "todo" and its quick start told
users to download models into the working directory; phase 3 still described
the caption window's close button as "quit" and used the wrong binary name.
Bring the docs up to date and fill the gaps: a GUI guide (first run, settings
tabs, tray, download, verify), a full CLI option reference marking the
test-only flags, a troubleshooting page, the model registry's size/sha256
fields plus a licence/size table, the RTF measurement caveat (llama-cli 0.19
vs the in-process 0.56), and a note that the streaming-ONNX backend has its
own code path. phase0/phase1 experiment docs are marked as historical.

文档与现状对齐:README 的 Phase 4 从「待做」改为完成、快速开始不再让人把模型下到当前
目录;phase3 的 ✕ 说明改为「隐藏到托盘」、用法改用 live-caption;新增 GUI/CLI/排错三份
文档;asr-backends 补上注册表的 size/sha256 字段与模型许可/体积表;phase0 补上 RTF 口径
说明(llama-cli 的 0.19 与程序内的 0.56);phase2 补上「流式 ONNX 走另一条分支」的说明。
This commit is contained in:
blumia committed 2026-10-12 17:29:45 +08:00
1 parent 370c869ad0
commit d234b9658d
12 files changed
+512 -57

No files matched your search

+5
View File
@@ -32,6 +32,11 @@
> 流式含义:模型常驻内存时,处理 2 秒窗口约 0.3 s,滑动窗口 + 提交策略下端到端延迟可做到 **~1 s 级**,与 Chrome 实时字幕同量级。
> **口径提示**:本页的 RTF ≈ 0.19 是 **`llama-cli` 纯生成**(`-t 8`)的数字。
> 程序内走 `libmtmd` 音频编码的实现,实测 RTF ≈ **0.56**(单线程,见
> [asr-backends.md](asr-backends.md#实测对比同一批音频1-线程));两个口径都远低于 1.0,
> 但引用数字时要注意区分。另外流式 ONNX 后端的 CPU 占用比它低约 35 倍。
### 2.1 0.6B vs 1.7B 实测对比
均为 Q8_0 主模型 + Q8_0 mmproj,`-t 8`。