bilibili-transcribe

Name: bilibili-transcribe
Author: chubbyguan

565stars81forks

How to install bilibili-transcribe?

chubbyguan/chubbyskills/bilibili-transcribe

$npx -y skills add chubbyguan/chubbyskills --skill bilibili-transcribe

Installs into the current project.

Summary

哔哩哔哩视频 → 下载 → 转录 → 存为 Markdown 的完整工作流。支持 BV 号和完整链接，无需登录。

Files · 1

View on GitHub

SKILL.md

1	# B 站视频转录 Skill
2
3	字幕优先：先尝试抓取官方/自动字幕（秒级、免 GPU、免 funasr）；抓不到再下载音频用 SenseVoice-Small 转录，存为 Markdown 文件。加 `--no-subtitle` 可强制走音频转录。
4
5	## 环境要求
6
7	```bash
8	# Python 3.9+
9	python -m venv .venv
10	source .venv/bin/activate
11
12	# 依赖
13	pip install funasr modelscope torch torchaudio
14
15	# 系统依赖
16	# macOS: brew install ffmpeg yt-dlp
17	# Ubuntu: sudo apt install ffmpeg && pip install yt-dlp
18	```
19
20	## 使用方法
21
22	```bash
23	python scripts/transcribe.py "https://www.bilibili.com/video/BV1rrQGBeEen/"
24	python scripts/transcribe.py "BV1rrQGBeEen"
25	python scripts/transcribe.py "BV1rrQGBeEen" --no-subtitle # 强制音频转录
26
27	# 批量处理：每行一个 B站 URL 或 BV 号
28	python scripts/batch_transcribe.py ../../examples/bilibili-urls.txt -o ./output
29	```
30
31	## 流程
32
33	### Step 1: yt-dlp 下载音频
34
35	B 站有反爬机制，需要加 User-Agent 和 Referer：
36
37	```bash
38	yt-dlp --extract-audio --audio-format mp3 --audio-quality 128K \
39	--user-agent "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) ..." \
40	--referer "https://www.bilibili.com" \
41	"https://www.bilibili.com/video/BV1rrQGBeEen/"
42	```
43
44	### Step 2: SenseVoice-Small 转录
45
46	```python
47	from funasr import AutoModel
48	from funasr.utils.postprocess_utils import rich_transcription_postprocess
49
50	model = AutoModel(
51	model="iic/SenseVoiceSmall",
52	trust_remote_code=True,
53	vad_model="fsmn-vad",
54	vad_kwargs={"max_single_segment_time": 30000},
55	device="cpu",
56	)
57
58	result = model.generate(input=audio_path, language="zh", use_itn=True, batch_size_s=60)
59	```
60
61	### Step 3: 生成 Markdown
62
63	自动创建带 frontmatter 的 Markdown 文件。
64
65	### 批量模式
66
67	`scripts/batch_transcribe.py` 会逐条调用单篇转录脚本，默认单条失败后继续处理下一条；需要严格模式时加 `--stop-on-error`。
68
69	## 性能数据
70
71	\| 视频时长 \| 转录耗时 \|
72	\|------\|------\|
73	\| 5 min \| ~10s \|
74	\| 10 min \| ~20s \|
75	\| 30 min \| ~60s \|
76
77	## 已知限制
78
79	- B 站 4K/1080P60 需要大会员，普通用户可下载 720P 以下
80	- SenseVoice-Small 模型首次下载约 893MB
81	- 不支持说话人分离
82	- 合集视频会下载第一个分 P
83
84	## 参考项目
85
86	- [yt-dlp/yt-dlp](https://github.com/yt-dlp/yt-dlp) - 视频下载工具
87	- [FunAudioLLM/SenseVoice](https://github.com/FunAudioLLM/SenseVoice) - 语音识别模型
88
89	## ⚖️ 合规声明
90
91	仅供个人学习与研究使用。请遵守目标平台的服务条款（ToS）与 robots 规则，控制请求频率，不要用于批量抓取、商用爬取或侵犯他人权益的场景。下载内容的版权归原作者所有。

People who liked this also viewed

6 picks

Type

ai-video-generationinference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agentsSkillsJul 2026292k642
imagegen-frontend-webElite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing pageSkillsJul 2026165k66k
hyperframes-mediaWrite HTML. Render video. Built for agents.SkillsJul 2026145k37k
media-useAgent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + leSkillsJul 2026144k37k
general-videoAuthor or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, staticSkillsJul 2026124k37k
product-launch-videoTurn a product or marketing URL, pasted script, or brief into a product launch / promo video — SaaS promos, feature reveals, product demos, app and company launches. Use when the user wants to market,SkillsJul 2026121k37k

bilibili-transcribe

565stars81forks

View on GitHub

How to install bilibili-transcribe?

chubbyguan/chubbyskills/bilibili-transcribe

$npx -y skills add chubbyguan/chubbyskills --skill bilibili-transcribe

Installs into the current project.

Summary

哔哩哔哩视频 → 下载 → 转录 → 存为 Markdown 的完整工作流。支持 BV 号和完整链接，无需登录。

Files · 1

View on GitHub

SKILL.md

1	# B 站视频转录 Skill
2
3	字幕优先：先尝试抓取官方/自动字幕（秒级、免 GPU、免 funasr）；抓不到再下载音频用 SenseVoice-Small 转录，存为 Markdown 文件。加 `--no-subtitle` 可强制走音频转录。
4
5	## 环境要求
6
7	```bash
8	# Python 3.9+
9	python -m venv .venv
10	source .venv/bin/activate
11
12	# 依赖
13	pip install funasr modelscope torch torchaudio
14
15	# 系统依赖
16	# macOS: brew install ffmpeg yt-dlp
17	# Ubuntu: sudo apt install ffmpeg && pip install yt-dlp
18	```
19
20	## 使用方法
21
22	```bash
23	python scripts/transcribe.py "https://www.bilibili.com/video/BV1rrQGBeEen/"
24	python scripts/transcribe.py "BV1rrQGBeEen"
25	python scripts/transcribe.py "BV1rrQGBeEen" --no-subtitle # 强制音频转录
26
27	# 批量处理：每行一个 B站 URL 或 BV 号
28	python scripts/batch_transcribe.py ../../examples/bilibili-urls.txt -o ./output
29	```
30
31	## 流程
32
33	### Step 1: yt-dlp 下载音频
34
35	B 站有反爬机制，需要加 User-Agent 和 Referer：
36
37	```bash
38	yt-dlp --extract-audio --audio-format mp3 --audio-quality 128K \
39	--user-agent "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) ..." \
40	--referer "https://www.bilibili.com" \
41	"https://www.bilibili.com/video/BV1rrQGBeEen/"
42	```
43
44	### Step 2: SenseVoice-Small 转录
45
46	```python
47	from funasr import AutoModel
48	from funasr.utils.postprocess_utils import rich_transcription_postprocess
49
50	model = AutoModel(
51	model="iic/SenseVoiceSmall",
52	trust_remote_code=True,
53	vad_model="fsmn-vad",
54	vad_kwargs={"max_single_segment_time": 30000},
55	device="cpu",
56	)
57
58	result = model.generate(input=audio_path, language="zh", use_itn=True, batch_size_s=60)
59	```
60
61	### Step 3: 生成 Markdown
62
63	自动创建带 frontmatter 的 Markdown 文件。
64
65	### 批量模式
66
67	`scripts/batch_transcribe.py` 会逐条调用单篇转录脚本，默认单条失败后继续处理下一条；需要严格模式时加 `--stop-on-error`。
68
69	## 性能数据
70
71	\| 视频时长 \| 转录耗时 \|
72	\|------\|------\|
73	\| 5 min \| ~10s \|
74	\| 10 min \| ~20s \|
75	\| 30 min \| ~60s \|
76
77	## 已知限制
78
79	- B 站 4K/1080P60 需要大会员，普通用户可下载 720P 以下
80	- SenseVoice-Small 模型首次下载约 893MB
81	- 不支持说话人分离
82	- 合集视频会下载第一个分 P
83
84	## 参考项目
85
86	- [yt-dlp/yt-dlp](https://github.com/yt-dlp/yt-dlp) - 视频下载工具
87	- [FunAudioLLM/SenseVoice](https://github.com/FunAudioLLM/SenseVoice) - 语音识别模型
88
89	## ⚖️ 合规声明
90
91	仅供个人学习与研究使用。请遵守目标平台的服务条款（ToS）与 robots 规则，控制请求频率，不要用于批量抓取、商用爬取或侵犯他人权益的场景。下载内容的版权归原作者所有。

People who liked this also viewed

6 picks

Type