Agent skill

Local Asr

by ysyecust in ysyecust/lecture-to-notes

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…

Custom licenceAuto-check passedAI & LLM Engineering

Install Local Asr

skills CLI
$ npx skills add ysyecust/lecture-to-notes --skill local-asr -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ysyecust/lecture-to-notes local-asr --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ysyecust/lecture-to-notes.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/lecture-to-md/local-asr .claude/skills/local-asr && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
local-asr
GitHub stars
273
Token cost
~1.6k tokens
SKILL.md length
377 words
Files
13 (incl. scripts, references)
Skills in repo
5
Repo updated
First seen
Licence
Custom licence

At a glance

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…

  • Works in 7 steps: 语言由用户指定;没说就默认中文(--lang zh),也支持 en / auto。 → 输出目录默认与源文件同目录,文件名取源文件同名干 → 模型不吃视频。入口脚本统一先用 ffmpeg 抽成 16 kHz 单声道 wav… → …
  • Tasks that involve Speech recognition and synthesis
  • SKILL.md covers 关键约定, 快速使用, 平台环境配置 and 参数, plus 4 more sections
  • Runs Python, PowerShell and Shell scripts from its folder; calls python3, bash and pip; reaches gh-proxy.com

What it does

Local Asr is an agent skill from ysyecust/lecture-to-notes. 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。

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 16 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/models.md` and `references/setup-linux.md`).

It sits in AI & LLM Engineering, covering Speech recognition and synthesis. It works with ONNX, macOS, Linux and PowerShell. The repository describes itself as: Turn YouTube/Bilibili lectures into smart-cropped LaTeX/PDF notes. Claude Code & Codex skill.

When your agent uses it

  • Tasks that involve Speech recognition and synthesis

Example prompts

  • “/local-asr”

Requirements

  • Python 3
  • A Bash shell
  • PowerShell

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  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
  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,
  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…
  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)。

What it can do on your machine

Read from SKILL.md and the folder at commit 0ef4e6f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 5 files in scripts/ (Python, PowerShell and Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • python3
    • bash
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • gh-proxy.com

    Also links to:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Local Asr loads about 1.6k tokens when it runs, and up to ~8.9k if it reads all its reference files. Until then it costs about 63 tokens; SKILL.md has 377 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 377 words (~1,622 tokens).

name
local-asr

Read the full SKILL.md on GitHub

Files

SKILL.md and 12 other files (scripts, references) in skills/lecture-to-md/local-asr of ysyecust/lecture-to-notes.

  • SKILL.md
  • .gitignore
  • agents/openai.yaml
  • references/models.md
  • references/setup-linux.md
  • references/setup-macos.md
  • references/setup-windows.md
  • scripts/common.py
  • scripts/setup.ps1
  • scripts/setup.sh
  • scripts/transcribe.py
  • scripts/transcribe_x_asr.py
  • tests/test_transcribe.py

Open the folder on GitHubat commit 0ef4e6f

Compare with similar skills

Local Asr next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Local Asr compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Local Asr this skillysyecust/lecture-to-notes273—~1.6kAutomated safety check: PassCustom licence
Local Asrcat-xierluo/legal-skills720—~5.8kAutomated safety check: PassMIT
Re AI Modeldslsdzc/rev-skills135—~2.4kAutomated safety check: PassApache-2.0
Remote Hostslibnativeapi/nativeapi164—~1.3kAutomated safety check: PassMIT
Crossreviewcoddy-project/coddy-agent168—~3.3kAutomated safety check: PassMIT
Environment SetupNorman-bury/research-writing-skill3.4k—~840Automated safety check: PassMIT

Similar skills

  • Local Asr

    cat-xierluo/legal-skills

    使用本地 ASR 服务将音频或视频文件转录为带时间戳和说话人的 Markdown,Apple Silicon 默认使用 MOSS-MLX,保留 FunASR 原生及 ONNX 管线供显式选择;支持认领式声纹注册,本人声纹注册后自动识别标注。支持 mp4、mov、mp3、wav、m4a 等格式;用于会议记录、电话录音、视频字幕和播客转录。

    720 GitHub stars~5.8k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Re AI Model

    dslsdzc/rev-skills

    AI 模型文件逆向与静态分析:ONNX/PyTorch/Safetensors/TFLite 格式解析、 网络结构还原、权重提取、文件级水印分析(权重 pattern/metadata/tensor hash/embedding 异常)。

    135 GitHub stars~2.4k tokensUpdated 5 days ago
    AI & LLM EngineeringAuto-check passed
  • Remote Hosts

    libnativeapi/nativeapi

    Build, run, and GUI-test on another machine over SSH — the user's Windows laptop today, Linux or other macOS machines tomorrow — with one symmetric CLI for every OS: push scripts, run them either in…

    164 GitHub stars~1.3k tokensUpdated today
    MobileAuto-check passed
  • Crossreview

    coddy-project/coddy-agent

    Run when the user invokes /crossreview (or /crossreview:setup to choose the reviewers) or asks for a cross-review, a quorum review or a second opinion from other agents or models: fan a code review…

    168 GitHub stars~3.3k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Environment Setup

    Norman-bury/research-writing-skill

    A skill your agent uses when Python environment setup is needed for data visualization or conda installation is required

    3.4k GitHub stars~840 tokensUpdated 4 mo ago
    Data & AnalyticsAuto-check passed
  • Murmur

    xiaopengde/murmur

    把一段中文(或任意 Whisper 支持语言)的会议/面试录音用本地 Whisper large-v3 转成文本,再清洗成带说话人标签、修过 ASR 错字、分好章节的 markdown 文档(可选再转成 docx)。跨平台(macOS Apple Silicon 用 mlx-whisper,Windows/Linux/Intel Mac 用…

    109 GitHub stars~2.9k tokensUpdated 4 mo ago
    AI & LLM EngineeringAuto-check: notes

More from ysyecust/lecture-to-notes

  • Volcengine Asr

    ysyecust/lecture-to-notes

    Transcribe local audio or video with Volcengine Doubao file ASR, including BigASR 1.0 Turbo direct upload and asynchronous 1.0 standard, 1.0 idle, or 2.0 standard jobs through TOS.

    273 GitHub stars~783 tokensUpdated 7 days ago
    Auto-check passed
  • Lecture To Md

    ysyecust/lecture-to-notes

    把课堂视频(本地或 B 站/YouTube)、文字稿、课件三者(任意组合)整理成一份详细的中文 Markdown 课堂笔记,输出按课程标题命名的 {titlename}.md(首行为 文档标题)+ 相对路径图片。Markdown 工作流,与上游 lecture-to-notes 的 LaTeX/PDF 输出并行存在;上游 skill 完全不动。触发词:markdown 笔记、md 笔记、视频转…

    273 GitHub stars~3.9k tokensUpdated 7 days ago
    Auto-check passed
  • Lecture To Notes

    ysyecust/lecture-to-notes

    A skill your agent uses when users provide YouTube, Bilibili, or X/Twitter lecture URLs and want reader-first Chinese LaTeX/PDF notes with source-faithful claims, fluent authored prose, and verified…

    273 GitHub stars~14k tokensUpdated 7 days ago
    Auto-check: notes
  • Paper To HTML

    ysyecust/lecture-to-notes

    Generate a self-contained, beautifully styled HTML analysis of an academic paper.

    273 GitHub stars~1.3k tokensUpdated 7 days ago
    Auto-check passed

Questions about Local Asr

What does Local Asr do?

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…. Local Asr is an agent skill from ysyecust/lecture-to-notes.

When should I use Local Asr?

Local Asr fits situations like: tasks that involve Speech recognition and synthesis.

How do I install Local Asr in Claude Code?

Run `npx skills add ysyecust/lecture-to-notes --skill local-asr -a claude-code`. Or copy the skill folder (skills/lecture-to-md/local-asr in ysyecust/lecture-to-notes) into .claude/skills/local-asr in your project. Claude Code loads it when a task matches its description.

How do I install Local Asr in Codex?

Run `npx skills add ysyecust/lecture-to-notes --skill local-asr -a codex`. Or copy the skill folder (skills/lecture-to-md/local-asr in ysyecust/lecture-to-notes) into .agents/skills/local-asr in your project. Codex loads it when a task matches its description.

Can I use Local Asr in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ysyecust/lecture-to-notes --skill local-asr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/local-asr, .gemini/skills/local-asr, .github/skills/local-asr and .opencode/skills/local-asr in your project.

What does Local Asr need to run?

Going by SKILL.md and its folder, Local Asr needs Python, PowerShell and a shell for the scripts in its folder and the command-line tools its instructions call (python3, bash and pip). Our summary lists: Python 3; A Bash shell; PowerShell.

Does Local Asr access the network?

SKILL.md names 2 domains. In commands or code: gh-proxy.com; the agent is likely to contact it when it follows the instructions. As links in the text: github.com. This is read from the text; nothing was executed.

Is Local Asr safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Local Asr use?

Local Asr has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Local Asr use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.3k tokens, read only when the agent opens those files.

What are the alternatives to Local Asr?

Skills that share tags, products or a category with Local Asr: Local Asr (cat-xierluo/legal-skills, 720 stars), Re AI Model (dslsdzc/rev-skills, 135 stars), Remote Hosts (libnativeapi/nativeapi, 164 stars) and Crossreview (coddy-project/coddy-agent, 168 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Local Asr?

ysyecust (a GitHub user) maintains it in ysyecust/lecture-to-notes, which has 273 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 3, 2026.

Source: ysyecust/lecture-to-notes on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.