mlfont-notosanstc: Range-Compact MLFont Slicing for Noto Sans TC (Traditional Chinese)

This is not an officially supported Google product.

Overview

Pretrained MLFont machine-learning-guided font slicing model and WOFF2 slice bundle for Noto Sans TC (Traditional Chinese) (NotoSansTC-Regular.otf, 20,637 Unicode codepoints partitioned into 82 range-compact slices).

• Paper: MLFont: Machine Learning-Driven Font Subsetting and Optimal Unicode-Range Slicing for Low-Latency Web Typography (Quan Wang and Yiran Mao)
• Open-Source Repository: https://github.com/wq2012/mlfont
• PyPI Package: https://pypi.org/project/mlfont/

Training Configuration

• Target Font: NotoSansTC-Regular.otf (20,637 Unicode codepoints)
• Training & Evaluation Corpus: wikimedia/wikipedia (20231101, languages: zh), 1,600 training articles and 400 uniformly sampled testing articles
• Slicing Architecture: Tiered Document-Frequency Slicing + Online Variational LDA & Deep Neural Network Topic Model (DNNTM) + Range-Compact Genetic Algorithm (mlfont preset: traditional_chinese)
• Total Slices: 82 slices (11,150 total CSS unicode-range intervals)
• Physical WOFF2 Bundle Size: 5.99 MB / 6129.8 KB (6,276,868 bytes) across 82 .woff2 files (companion CSS: 121.7 KB)
• Training Wall-Time: 62.0 seconds on CPU/GPU

Model Files Included

• model.safetensors: Learned topic-codepoint weight matrices (lambda_matrix, dnntm_lambda_matrix), codepoints, remaining_codepoints, frequency_array, and dna_assignment in SafeTensors format
• strategy.json: Range-Compact GA SlicingStrategy definition and hyperparameters
• olda_strategy.json: Online LDA + Greedy SlicingStrategy definition
• dnntm_strategy.json: DNNTM (Entropy Difference Loss) + Greedy SlicingStrategy definition
• test_samples.json: Exact held-out evaluation codepoint sets (400 test pages)
• config.json: Model and font bundle summary metadata (including per-slice WOFF2 byte sizes)
• font_sliced.css: Production-ready @font-face stylesheet with compact unicode-range descriptors
• woff2/*.woff2: 82 physical WOFF2 font slices generated via fontTools.subset
• nam/*.nam: 82 Google Fonts .nam codepoint subset files
• evaluation_metrics.json: Full benchmark metrics across all 7 network/session profiles

Benchmark Performance (400 Wikipedia Test Pages, Session Length L = 10)

Strategy	Slices	CSS Ranges	Missing (Eval / Font)	GIN-2g Mean / P95 (ms)	GIN-3g Mean / P95 (ms)	DSL Mean / P95 (ms)	Session Util (%)
single_slice	1	5036	0 / 0	125.58 / 704.12	31.43 / 176.24	6.28 / 35.18	7.88%
equal_bin_82	82	5098	0 / 0	115.29 / 689.78	31.03 / 185.64	5.54 / 33.17	9.67%
random_slice_82	82	20436	0 / 0	144.57 / 922.42	38.91 / 248.25	6.95 / 44.36	7.88%
language_slice	10	5767	126 / 11699	52.25 / 282.95	13.23 / 71.40	2.60 / 14.08	18.89%
most_600_600_equal_bin_80	82	6672	0 / 0	92.66 / 446.08	24.90 / 119.91	4.46 / 21.47	9.83%
online_lda_topics80_greedy	82	11867	0 / 0	50.11 / 250.61	13.43 / 67.58	2.42 / 12.04	19.59%
dnntm_topics80_greedy	82	11410	0 / 0	51.65 / 226.65	13.84 / 60.72	2.49 / 10.93	19.30%
range_compact_most600_600_topics80 (This Model)	82	11150	0 / 0	56.02 / 267.26	14.99 / 71.75	2.70 / 12.87	16.93%

Usage

Install mlfont:

pip install mlfont huggingface_hub

Load the pretrained bundle (Range-Compact GA, Online LDA, and DNNTM) in Python:

import mlfont

bundle = mlfont.load_pretrained("wq2012/mlfont-notosanstc")
print("GA:", bundle.strategy.name, "ranges:", bundle.strategy.count_unicode_ranges())
print("LDA:", bundle.olda_strategy.name, "ranges:", bundle.olda_strategy.count_unicode_ranges())
print("DNNTM:", bundle.dnntm_strategy.name, "ranges:", bundle.dnntm_strategy.count_unicode_ranges())

Citation

@article{wang2017learning,
  title={Learning Better Font Slicing Strategies from Data},
  author={Wang, Quan and Mao, Yiran},
  journal={Technical Disclosure Commons, Defensive Publications Series},
  volume={906},
  year={2017}
}