Game-Translator
Assassin's Creed Unity Subtitle
logo
LOCALIZATION MOD
RELEASED vExperimental-1 Austronesian Lang

Assassin's Creed Unity Subtitle Assassin's Creed Unity Subtitle

Bahasa Indonesia, Melayu, Filipino

Paris, 1789. In this action-adventure game, experience the French Revolution through the eyes of Arno Dorian. Become an Assassin and expose the true powers behind the Revolution for the fate of a nation in Indonesia, Melayu, or Filipino narrative.

Product Narrative

The Full Story

Still in experimental-1, and maybe few of lines has hallucinations. maybe i should redo all the translations if this mod gain tractions. For patch 1.5.0;

Current Milestone

Available Now

Author's Notes


Linguistic Analysis Report

Stylometric Register Analysis

Discourse analysis using Gemma embeddings. Classifies rhetorical register across the corpus to ensure tonal consistency with source narrative assets.

Casual
51.8%
Standard
18.9%
Formal
29.4%
Emotional Spectrum

Emotional tone mapped via dot-product similarity between extracted dialog embeddings and predefined sentiment anchors using zero-shot semantic alignment.

Neutral/Functional
27.3%
Stoic/Restrained
25.2%
Positive/Warm
22.8%
Negative/Intense
14.0%
Complex/Ambivalent
10.7%
Archetypes
21 detected
Bishop
18.4%
Npc
17.5%
Bellec
11.9%
De Sade
10.9%
Élise
6.2%
Arno
5.7%
Germain
5.7%
Robespierre
4.1%
Rebecca
3.5%
Shaun
3.1%
NapolÉon
2.7%
Sivert
2.2%
System
1.9%
Mirabeau
1.5%
De La Serre
1.4%
La Touche
0.8%
Roi Des Thunes
0.6%
Le Peletier
0.5%
Marie
0.5%
Ui
0.5%
English_subtitles
0.5%

DISCLOSURE: Profiling data generated algorithmically via zero-shot inference and semantic vector alignment. Represents AI interpretation of the dataset corpus, not explicit ground-truth statistics from the underlying game engine or internal metrics. Use as a heuristic guide for context mapping.

Cross-Lingual Quality Matrix

Semantic alignment quantified via Multilingual E5 Large Instruct (RoBERTa based) bitext mining. NER entities preserved using GLiNER heuristic extraction protocols to maintain terminological invariance.

ID
Indonesian
19,063 / 19,485 lines
98%
Semantic Sim.
82 %
Lex. Density
73.3 %
src
72.7%
Lex. Diversity
7.5 %
src
7.7%
MS
Malay
19,154 / 19,485 lines
98%
Semantic Sim.
81 %
Lex. Density
73.8 %
src
72.7%
Lex. Diversity
5.9 %
src
7.7%
TL
Tagalog
18,833 / 19,485 lines
97%
Semantic Sim.
79 %
Lex. Density
60.5 %
src
72.7%
Lex. Diversity
6.9 %
src
7.7%

* Sim = Cosine Similarity (Vector Space) · Density = Content/Total Tokens · Diversity = TTR (Type-Token Ratio) · "src" = Source Baseline · Named Entities enforced via GLiNER mining.

Corpus Volume & Metrics
57,714 Token Lines
Src Density
72.7%
Src Diversity
7.7%
Syntactic Error Report

Heuristic markup verification utilizing multi-pass validation and correction to ensure syntactical integrity of control codes and visual tags.

230
Mismatch
230
Fixed
0
Partial

Name

Label
Retrieving Portrait...
Narrative Profile

Associated Entities
Semantic Archetypes

NLP Pipeline Intelligence

Video Logs

Featured Preview Auto-Detected

Line Identity 0
Source (English)
Loading...
Indonesian (ID)
Loading...
Malay (MS)
Loading...
Tagalog (TL)
Loading...

Pipeline Receipts

Merger (S7) 2026-03-03 12:54
Tag Repair (S6) 2026-03-02 16:52
Validator (S5) 2026-03-02 16:40
Corrector (S3) 2026-03-02 15:30
Re-Import (S4) 2026-03-02 15:27
Translator (S2) 2026-03-02 14:26
Tagger (S1) 2026-03-02 12:08
Splitter (S0) 2026-03-02 11:20

Released Archive

Austronesian Showcase

Location
Image
Video