Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
The Great Language Game
Search
Lars Yencken
September 02, 2013
Programming
0
330
The Great Language Game
A brief introduction to the Great Language Game, given to the Melbourne Python User Group.
Lars Yencken
September 02, 2013
Tweet
Share
More Decks by Lars Yencken
See All by Lars Yencken
Linguistics, a whirlwind tour!
larsyencken
0
61
Pycon 2014 Recap
larsyencken
0
68
Nine months of food
larsyencken
0
290
Automation for web development
larsyencken
0
160
Scaling a web stack
larsyencken
4
200
Similarity metrics for Japanese kanji
larsyencken
0
87
Other Decks in Programming
See All in Programming
AI 駆動開発ライフサイクル(AI-DLC):ソフトウェアエンジニアリングの再構築 / AI-DLC Introduction
kanamasa
11
5.3k
MDN Web Docs に日本語翻訳でコントリビュート
ohmori_yusuke
0
440
はじめてのカスタムエージェント【GitHub Copilot Agent Mode編】
satoshi256kbyte
0
160
re:Invent 2025 トレンドからみる製品開発への AI Agent 活用
yoskoh
0
630
AtCoder Conference 2025
shindannin
0
930
TerraformとStrands AgentsでAmazon Bedrock AgentCoreのSSO認証付きエージェントを量産しよう!
neruneruo
4
2.4k
【卒業研究】会話ログ分析によるユーザーごとの関心に応じた話題提案手法
momok47
0
170
.NET Conf 2025 の興味のあるセッ ションを復習した / dotnet conf 2025 quick recap for backend engineer
tomohisa
0
110
Deno Tunnel を使ってみた話
kamekyame
0
320
組み合わせ爆発にのまれない - 責務分割 x テスト
halhorn
1
180
LLMで複雑な検索条件アセットから脱却する!! 生成的検索インタフェースの設計論
po3rin
4
1.1k
Claude Codeの「Compacting Conversation」を体感50%減! CLAUDE.md + 8 Skills で挑むコンテキスト管理術
kmurahama
1
740
Featured
See All Featured
Leveraging LLMs for student feedback in introductory data science courses - posit::conf(2025)
minecr
0
120
Groundhog Day: Seeking Process in Gaming for Health
codingconduct
0
75
Deep Space Network (abreviated)
tonyrice
0
34
Why You Should Never Use an ORM
jnunemaker
PRO
61
9.7k
Designing Powerful Visuals for Engaging Learning
tmiket
0
200
How to optimise 3,500 product descriptions for ecommerce in one day using ChatGPT
katarinadahlin
PRO
0
3.4k
Git: the NoSQL Database
bkeepers
PRO
432
66k
Agile Actions for Facilitating Distributed Teams - ADO2019
mkilby
0
100
The World Runs on Bad Software
bkeepers
PRO
72
12k
Building the Perfect Custom Keyboard
takai
2
670
Put a Button on it: Removing Barriers to Going Fast.
kastner
60
4.1k
Redefining SEO in the New Era of Traffic Generation
szymonslowik
1
190
Transcript
. . . .. . . . .. . .
. .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . . .. . . . .. . . . .. . The Great Language Game Lars Yencken Melbourne Python User Group September 2, 2013
. . . .. . . . .. . .
. .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . . .. . . . .. . . . .. . I’m a language geek
. . . .. . . . .. . .
. .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . . .. . . . .. . . . .. . I’m a human language geek
. . . .. . . . .. . .
. .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . . .. . . . .. . . . .. . The world has something like 7,000 languages
. . . .. . . . .. . .
. .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . . .. . . . .. . . . .. . The world has something like 7,000 languages So many!
. . . .. . . . .. . .
. .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . . .. . . . .. . . . .. . The world has something like 7,000 languages Too many to learn!
. . . .. . . . .. . .
. .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . . .. . . . .. . . . .. . But... with the help of a lil Python we can at least learn to tell the difference between languages
. . . .. . . . .. . .
. .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . . .. . . . .. . . . .. . Aside: langid.py Distinguish between languages in text form
. . . .. . . . .. . .
. .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . . .. . . . .. . . . .. . Aside: langid.py Distinguish between languages in text form ผู้สื่อข่าวไทยวิเคราะห์นโยบายผู้ขอลี้ภัยพรรคต่างๆ >>> import langid >>> langid.classify(l.encode(’utf8’)) (’th’, 1.0) >>> langid.classify(’¡Venga hombre!’) (’es’, 0.5726778160604622)
. . . .. . . . .. . .
. .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . . .. . . . .. . . . .. . First attempt: streaming radio ▶ There’s lots of internet radio out there! ▶ But it’s all in shitty old formats ▶ And Python support for decoding them all is not great ▶ Solution: sh module and mplayer ▶ Still too hard!
. . . .. . . . .. . .
. .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . . .. . . . .. . . . .. . Second attempt: scrape SBS ▶ Podcasts News podcasts in about 70 languages ▶ Good quality recordings! ▶ (Sometimes) daggy Australian accents ▶ Fetching: pyquery, requests and parse ▶ Processing audio: wave + sh wrapping avconv and mp3gain ▶ Success!
. . . .. . . . .. . .
. .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . . .. . . . .. . . . .. . Aside: sh Wraps shell calls like a boss! >>> from sh import ffmpeg >>> ffmpeg(’-i’, input_file, output_file) >>> from sh import mp3gain >>> mp3gain(’-r’, ’-k’, ’-t’, ’-s’, ’r’, sound_file)
. . . .. . . . .. . .
. .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . . .. . . . .. . . . .. . More about languages ▶ Wikipedia: manual data entry ▶ Freebase API: via requests
. . . .. . . . .. . .
. .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . . .. . . . .. . . . .. . End result: demo time!
. . . .. . . . .. . .
. .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . .. . . . .. . . . . .. . . . .. . . . . .. . . . .. . . . .. . Thanks http://greatlanguagegame.com/