AI Rank
EN
← 开源
haltakov

natural-language-youtube-search

Search inside YouTube videos using natural language

ApplicationsOtherJupyter Notebook
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
936
Star
70
Fork
+0
本周
3
贡献者
创建于 2021-02-01 · 更新于 2026-10-02 · 今日第 12531 名
主要开发者
haltakovAK391matiastucci

haltakov/natural-language-youtube-search 排名第 12,531，有 936 个星标。

同类别比较

haltakov/natural-language-youtube-search 排名第 12,531，此处有 8 个同类条目；777genius/claude-code-source-code 排名第 12,532。

同类别比较
名称排名指标
nexu-io/codex-slides12,516
语言:
TypeScript
星标数:
938
分叉数:
80
gannonh/chatgpt-pgvector12,522
语言:
TypeScript
星标数:
937
分叉数:
125
简介:
ChatGTP (gpt3.5-turbo) starter app
investbrainapp/investbrain12,523
语言:
PHP
星标数:
937
分叉数:
73
简介:
Smart LLM-enabled investment tracker that consolidates and monitors market performance across your different brokerages
pgosar/ChatGDB12,525
语言:
Python
星标数:
937
分叉数:
32
简介:
Harness the power of ChatGPT inside the GDB or LLDB debugger!
777genius/claude-code-source-code12,532
星标数:
935
分叉数:
1,082
简介:
Claude code source code
Renset/macai12,536
语言:
Swift
星标数:
935
分叉数:
76
简介:
All-in-one native macOS AI chat application for virtually any AI provider
dpressel/rude-carnie12,543
语言:
Python
星标数:
934
分叉数:
333
简介:
Age detection in Tensorflow
marcelo-earth/generative-manim12,548
语言:
Python
星标数:
933
分叉数:
137
简介:
🎨 GPT for video generation ⚡️
关键参数与规格
关键参数与规格
参数值
语言Jupyter Notebook
类别Applications
子类别Other
关键词Search
星标数936
分叉数70
贡献者3
创建日期2021-02-01
更新日期2026-10-02
1 天星标数0
7 天星标数0
排名12,531
上次排名12,454
排名变化-77
7 天星标排名13,473
上次 7 天星标排名13,483
7 天星标排名变化10
总星标排名11,720
上次总星标排名11,703
总星标排名变化-17
国家Germany
README 摘录

Natural Language YouTube Search Use OpenAI's CLIP neural network to search inside YouTube videos. You can try it by running the notebook on Google Colab. Encode a natural language search query using CLIP 5. Find the images that best match the search query For more details see the notebook. Examples Here are some example searches from this YouTube video of a car driving around San Francisco. "A fire truck" "Road works" "People crossing the street" "The Embarcadero" "Waiting at the

red light" "Green bike lane" "A street with tram tracks" "The Transamerica Pyramid" Natural language search on Unsplah You can also try my other project to search from 2M photos on Unsplash using natural language queries: Natural Language Image Search

常见问题

记录了多少星标和分叉？

haltakov/natural-language-youtube-search 有 936 个星标和 70 个分叉。

仓库排名是多少？

haltakov/natural-language-youtube-search 排名第 12,531。

记录的语言和类别是什么？

haltakov/natural-language-youtube-search 有 936 个星标，语言为 Jupyter Notebook，类别为 Applications。

哪个仓库排名最接近？

haltakov/natural-language-youtube-search 与 777genius/claude-code-source-code 比较，后者排名第 12,532，有 935 个星标。

README

Natural Language YouTube Search

Use OpenAI's CLIP neural network to search inside YouTube videos. You can try it by running the notebook on Google Colab.

New

How it works

  1. Download the YouTube video
  2. Extract every N-th frame
  3. Encode all frames using CLIP
  4. Encode a natural language search query using CLIP
  5. Find the images that best match the search query

For more details see the notebook.

Examples

Here are some example searches from this YouTube video of a car driving around San Francisco.

"A fire truck"

"Road works"

"People crossing the street"

"The Embarcadero"

"Waiting at the red light"

"Green bike lane"

"A street with tram tracks"

"The Transamerica Pyramid"

Natural language search on Unsplah

You can also try my other project to search from 2M photos on Unsplash using natural language queries:

Natural Language Image Search

排名相邻
同类项目