local-asr SKILL.md skillA
local-asr from ysyecust/lecture-to-notes is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ysyecust/lecture-to-notes/local-asr@git:20260905.7dcad9cPins git:20260905.7dcad9c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ysyecust/lecture-to-notes
- Path
skills/lecture-to-md/local-asr/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260905.7dcad9c, committed Sep 5, 2026
- Size
- 9,115 bytes
- Repository stars
- 301
- License
- a license file GitHub does not identify
把本地长视频/音频转写成文字稿 + 可选字幕，纯本地（不上传云端），用 sherpa-onnx X-ASR Zipformer transducer 模型（int8 量化、中英双语、自动标点）。已在 macOS Apple Silicon（int8 + AMX，~100× 实时）、Linux ARM64（CPU，~32× 实时）与 Windows（PowerShell 5.1，CPU）端到端验证。使用 `$lecture-to-md` 默认 ASR 后端；默认不要换成 Qwen。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Local ASR Transcribe（`lecture-to-md` 子 skill，sherpa-onnx X-ASR） 在本地（macOS Apple Silicon、Linux ARM64、Windows 均已端到端验证）把**长课程视频/音频**转成文字稿，可选补时间戳出字幕。单一后端，中英文通用： ```text 中文/英文 ──→ sherpa-onnx OfflineRecognizer (X-ASR Zipformer transducer, int8) ──→ 文本 + token 级时间戳 ──→ txt / md / srt / vtt ``` 前提只要：`ffmpeg` / `ffprobe`、`python3`、`sherpa-onnx` pip 包、X-ASR 模型权重。**首次使用按平台看对应的 reference**：macOS / Linux 跑 `bash scripts/setup.sh` 一键完成；Windows 原生 PowerShell 用户跑 `.\scripts\setup.ps1`。详细步骤与故障排查见「[平台环境配置](#平台环境配置)」一节。 ## 关键约定 1. **语言由用户指定；没说就默认中文**（`--lang zh`），也支持 `en` / `auto`。 2. **输出目录默认与源文件同目录**，文件名取源文件同名干： `课程.mp4` → `课程.txt` / `课程.md`；加 `--timestamps` 后再生成 `课程.srt` 或 `课程.vtt`。 3. **模型不吃视频**。入口脚本统一先用 ffmpeg 抽成 16 kHz 单声道 wav 再送模型， 视频、m4a、mp3、wav 都一样处理，不用手工转码。 4. 已存在同名输出时**不覆盖**，需显式加 `--overwrite`。 5. **sherpa-onnx X-ASR 默认产出 token 级时间戳**（Zipformer transducer 自带对齐能力，无需独立 ForcedAligner 模型），所以 `--timestamps` 不带来额外权重、也不多花一倍时间。CLI 要字幕就加 `--timestamps`；skill 调用默认会加。 6. **调用本 skill 时默认加 `--timestamps`**，确保产出带时间轴的字幕；只有用户明确只要纯文本时才省略。 7. **已有稿子想补时间戳**：直接对原音频跑一次 `transcribe.py --timestamps --formats srt,vtt`，拿生成的 srt 作为字幕时间轴，文本再用原稿覆盖（sherpa-onnx 不需要独立强制对齐模型）。 ## 快速使用 ```bash …
Read the whole file at its exact version.
How to install
mdr add ysyecust/lecture-to-notes/local-asr@sha256:298a1bc28a67dc80The line at the top of this page pins the label git:20260905.7dcad9c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_zjqys6npqau2x6nt)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 5, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9115 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ysyecust/lecture-to-notes · 301 stars · license a license file GitHub does not identify · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_zjqys6npqau2x6nt GET https://markdownregistry.com/api/v1/resolve?ref=ysyecust/lecture-to-notes/local-asr GET https://markdownregistry.com/api/v1/blob/298a1bc28a67dc800ad054b7c83a8341781582f3d4a31e3227d3c3f4466e9df6
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from ysyecust/lecture-to-notes
Every file in ysyecust/lecture-to-notes