A tool for mining sentences from games. Update: Dependencies, replay buffer based line searching, and bug fixes.

Navigation

Verified details

These details have been verified by PyPI
Maintainers
Avatar for Beangate from gravatar.com Beangate

Unverified details

These details have not been verified by PyPI
Project links
Meta
  • License: MIT License (MIT License)
  • Author: Beangate
  • Requires: Python <3.14, >=3.10
  • Provides-Extra: lens , gpu , dev
Classifiers
Report project as malware

Project description

gamesentenceminer

GSM (GameSentenceMiner)

Turn your gaming time into language mastery.

🎮 See it in Action

Demo Gif

  • OCR to get get text from a game that doesn't support text hooks.
  • Look up words with Yomitan in game.
  • Create Anki cards with game audio + screenshot (or gif) automatically.

What does it do?

GSM is an application designed to automate the process of creating flashcards while you play. It sits between your game and Anki, handling audio recording, screenshots, and OCR so you don't have to interrupt your gameplay.

📝 Anki Card Enhancement

GSM automatically adds context to your Anki cards whenever you create them.

  • Audio Capture: Uses Voice Activity Detection (VAD) to record and trim the specific voice line associated with the text.
  • Screenshots: Captures the game state the moment the line is spoken. GIFs and Black Bar Removal are supported.
  • Mine from History: Go back and create cards from previous lines you've encountered (i.e. cutscenes).
  • Multi-Line Support: Capture multiple lines of dialogue into one card using the built-in Texthooker.
  • AI Translation: Optional integration to provide sentence translations using your own API key.

https://github.com/user-attachments/assets/df6bc38e-d74d-423e-b270-8a82eec2394c

👁️ OCR (Text Recognition)

For games that don't have a text hook (Agent/Textractor), GSM uses a custom fork of OwOCR to read text directly from the screen.

This opens up all kinds of posssibilities for games that would otherwise be inaccessible for language learning/sentence mining. For example I've made cards with games like Metal Gear Solid 1+2, Titanfall 2, and Sekiro, all using GSM's OCR.

  • Easy Setup: Managed installation means you don't need to fiddle with terminals.
  • Two-Pass System: Clean, fast output similar to as if you had a hook.
  • Customizable Capture Zones: Define exactly where text appears on your screen for optimal results.

https://github.com/user-attachments/assets/07240472-831a-40e6-be22-c64b880b0d66

🖥️ Overlay

GSM includes a transparent overlay for instant dictionary lookups.

  • Hover over characters in-game to see definitions via Yomitan.
  • Create cards without ever leaving the game window.
  • Automatically Generated Furigana Display In Game.

Overlay Demo

📊 Statistics

Track your immersion habits with the stats dashboard.

  • Kanji Grid: View every Kanji you've encountered and click them to see their source sentences.
  • Goals: Set daily reading targets.
  • Tools: Clean up and organize your mining history.

stats

🚀 Getting Started

  1. Download: Get the latest release.
  2. Install: Watch the Installation Guide.
  3. Requirements:
    • An Anki tool (Yomitan, JL, etc.)
    • A text source (Agent, Textractor, or GSM's built-in OCR)
    • A game

📚 Documentation

For full setup guides and configuration details, check the Wiki (Currently WIP).

❤️ Acknowledgements

Integrated Components

This project includes modified versions of the following libraries, I got tired of submodule hell so I've included them directly here for easier management all credits go to the original authors:

Star History

Star History Chart

Project details

Verified details

These details have been verified by PyPI
Maintainers
Avatar for Beangate from gravatar.com Beangate

Unverified details

These details have not been verified by PyPI
Project links
Meta
  • License: MIT License (MIT License)
  • Author: Beangate
  • Requires: Python <3.14, >=3.10
  • Provides-Extra: lens , gpu , dev
Classifiers

Release history Release notifications | RSS feed

2026.5.4

2026.5.3

2026.5.2

This version

2026.4.8

2026.4.7

2026.4.6

2026.4.5

2026.4.4

2026.4.3

2026.4.2

2026.4.1

2026.3.23

2026.3.22

2026.3.21

2026.3.13

2026.3.1

2026.3.0

2.24.7

2.24.6

2.24.5

2.24.4

2.24.3

2.24.2

2.24.1

2.24.0

2.23.34

2.23.33

2.23.32

2.23.31

2.23.30

2.23.29

2.23.28

2.23.27

2.23.25

2.23.24

2.23.23

2.23.22

2.23.21

2.23.20

2.23.19

2.23.18

2.23.17

2.23.16

2.23.15

2.23.14

2.23.13

2.23.12

2.23.11

2.23.10

2.23.9

2.23.8

2.23.7

2.23.6

2.23.5

2.23.4

2.23.3

2.23.2

2.23.1

2.23.0

2.22.19

2.22.18

2.22.17

2.22.16

2.22.15

2.22.14

2.22.13

2.22.11

2.22.10

2.22.9

2.22.8

2.22.7

2.22.6

2.22.5

2.22.4

2.22.3

2.22.2

2.22.1

2.22.0

2.21.36

2.21.35

2.21.34

2.21.33

2.21.32

2.21.31

2.21.30

2.21.29

2.21.28

2.21.27 yanked

Reason this release was yanked:

im silly

2.21.26

2.21.25

2.21.24

2.21.23

2.21.22

2.21.21

2.21.20

2.21.19

2.21.18

2.21.17

2.21.16

2.21.15

2.21.14

2.21.13

2.21.12

2.21.11

2.21.10

2.21.9

2.21.8

2.21.7

2.21.6

2.21.5

2.21.4

2.21.3

2.21.2

2.21.1

2.21.0

2.20.10

2.20.9

2.20.8

2.20.7

2.20.6 yanked

Reason this release was yanked:

broken dep

2.20.5

2.20.4

2.20.3

2.20.2

2.20.1

2.20.0

2.19.17

2.19.16

2.19.15

2.19.14

2.19.13

2.19.12

2.19.11

2.19.10

2.19.9

2.19.8

2.19.7

2.19.6

2.19.5

2.19.4

2.19.3

2.19.2.dev0 pre-release

2.19.1

2.19.0

2.18.21

2.18.20

2.18.19

2.18.18

2.18.17

2.18.16

2.18.15

2.18.14

2.18.13

2.18.12

2.18.11

2.18.10

2.18.9

2.18.8

2.18.7

2.18.6

2.18.5

2.18.4

2.18.3

2.18.2

2.18.1

2.18.0

2.17.7

2.17.6

2.17.5

2.17.4

2.17.3

2.17.2

2.17.1

2.17.0

2.16.13

2.16.12

2.16.11

2.16.10

2.16.9

2.16.8

2.16.7

2.16.6

2.16.5

2.16.4

2.16.3

2.16.2

2.16.1

2.16.0

2.15.12

2.15.11

2.15.10

2.15.9

2.15.8

2.15.7

2.15.6

2.15.5

2.15.4

2.15.3

2.15.2

2.15.1

2.15.0

2.14.21

2.14.20

2.14.19

2.14.18

2.14.17

2.14.16

2.14.15

2.14.14

2.14.13

2.14.12

2.14.11

2.14.10

2.14.9

2.14.8

2.14.7

2.14.6

2.14.5

2.14.4

2.14.3

2.14.2

2.14.1

2.14.0

2.14.0rc1 pre-release

2.13.15

2.13.14

2.13.13

2.13.12

2.13.11

2.13.10

2.13.9

2.13.8

2.13.7.post1

2.13.7

2.13.6

2.13.5.post1

2.13.5

2.13.4.post2

2.13.4.post1

2.13.4

2.13.3

2.13.2.post1

2.13.2

2.13.1

2.13.0

2.12.12.post1

2.12.12

2.12.11

2.12.10

2.12.9

2.12.8

2.12.7.post1

2.12.7

2.12.6

2.12.6.dev0 pre-release

2.12.5

2.12.4

2.12.3

2.12.2

2.12.1

2.12.0

2.12.0.dev6 pre-release

2.12.0.dev5 pre-release

2.12.0.dev4 pre-release

2.12.0.dev3 pre-release

2.12.0.dev2 pre-release

2.12.0.dev1 pre-release

2.11.8

2.11.7

2.11.6

2.11.5

2.11.4

2.11.3

2.11.2

2.11.1

2.11.0

2.10.17

2.10.16

2.10.15

2.10.14

2.10.13

2.10.12

2.10.11

2.10.10

2.10.9

2.10.8 yanked

Reason this release was yanked:

broken

2.10.7 yanked

Reason this release was yanked:

broken

2.10.6

2.10.5

2.10.4

2.10.3

2.10.2

2.10.1

2.10.0

2.9.29

2.9.28

2.9.27

2.9.26

2.9.25

2.9.24

2.9.23

2.9.22

2.9.21

2.9.20

2.9.19

2.9.18

2.9.17

2.9.16

2.9.15

2.9.14

2.9.13

2.9.12

2.9.11

2.9.10

2.9.9

2.9.8

2.9.7

2.9.6

2.9.5

2.9.4

2.9.3

2.9.2

2.9.1

2.9.0

2.8.54

2.8.53

2.8.52

2.8.51

2.8.50

2.8.49

2.8.48

2.8.47

2.8.46

2.8.45

2.8.44

2.8.43

2.8.42

2.8.41

2.8.40

2.8.39

2.8.38

2.8.37

2.8.36

2.8.35

2.8.34

2.8.33

2.8.31

2.8.30

2.8.29

2.8.28

2.8.27

2.8.26

2.8.25

2.8.24

2.8.23

2.8.22

2.8.21

2.8.20

2.8.19

2.8.18

2.8.17

2.8.16

2.8.15

2.8.14

2.8.13

2.8.12

2.8.11

2.8.10

2.8.9

2.8.8

2.8.7

2.8.6

2.8.5

2.8.4

2.8.3

2.8.2

2.8.1

2.8.0

2.7.17

2.7.16

2.7.15

2.7.14

2.7.13

2.7.12

2.7.11

2.7.10

2.7.9

2.7.8

2.7.7

2.7.6

2.7.5

2.7.4

2.7.3

2.7.2

2.7.1

2.7.0

2.6.5

2.6.4

2.6.3

2.6.2

2.6.1

2.6.0

2.5.14

2.5.13

2.5.12

2.5.11

2.5.10

2.5.9

2.5.8

2.5.7

2.5.6 yanked

Reason this release was yanked:

Missing package

2.5.5

2.5.4

2.5.3

2.5.2

2.5.1

2.5.0

2.4.12

2.4.10

2.4.9

2.4.8

2.4.7

2.4.6

2.4.5

2.4.4

2.4.3

2.4.2

2.4.1

2.4.1.dev1 pre-release

2.4.0

2.3.8

2.3.7

2.3.6

2.3.5

2.3.4

2.3.3

2.3.2

2.3.1 yanked

Reason this release was yanked:

dumb imports

2.3.0 yanked

Reason this release was yanked:

was trying to use previous audio when it shouldn't have been

2.2.4

2.2.3

2.2.2.post2

2.2.2.post1

2.2.2

2.2.1

2.2.0 yanked

Reason this release was yanked:

using wrong ffprobe command

2.1.2.post1

2.1.2 yanked

Reason this release was yanked:

Broken

2.1.1.post1

2.1.1

2.1.0

2.0.1.post2

2.0.1.post1

2.0.1

0.0.0.dev0 pre-release

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gamesentenceminer-2026.4.8.tar.gz (28.7 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

gamesentenceminer-2026.4.8-py3-none-any.whl (29.0 MB view details)

Uploaded Python 3

File details

Details for the file gamesentenceminer-2026.4.8.tar.gz.

File metadata

  • Download URL: gamesentenceminer-2026.4.8.tar.gz
  • Upload date:
  • Size: 28.7 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.15

File hashes

Hashes for gamesentenceminer-2026.4.8.tar.gz
Algorithm Hash digest
SHA256 3408a1abd6c8b531fcb563a1b72b451d010a23dd46798b040bbc631fa42b339c
MD5 c27c5457542980d3502fe8c8fcd710c4
BLAKE2b-256 fd6dfb1026a9f00d75c1435755a7688a6d19bb529c77fcdcb637d4bc28c4102d

See more details on using hashes here.

File details

Details for the file gamesentenceminer-2026.4.8-py3-none-any.whl.

File metadata

File hashes

Hashes for gamesentenceminer-2026.4.8-py3-none-any.whl
Algorithm Hash digest
SHA256 c4c5bf861564edf7401a17ae5f7a5cb613604256b1e010c884ef7123ffcc1881
MD5 2e61469d83ed15688ffd91169f7952f4
BLAKE2b-256 4b5a3b25b08bc8ccef1308dcf04d22c92a6ea971bcfc6d47f051b7ea3a36cc06

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page