Thulium

State-of-the-art multilingual handwriting text recognition.

Thulium is a production-ready Python library for offline handwritten text recognition (HTR) supporting 52+ languages across Latin, Cyrillic, Greek, Arabic, Hebrew, Devanagari, Chinese, Japanese, Korean, and Georgian scripts.

Features

52+ Languages — Comprehensive multilingual support with script-aware processing
Production Ready — Optimized inference with ONNX export and mixed precision
State-of-the-Art — CNN/ViT backbones with Transformer/LSTM sequence heads
Explainable AI — Attention visualization, saliency maps, and confidence analysis
Flexible Decoding — CTC beam search with n-gram and neural language models

Installation

pip install thulium

For GPU acceleration:

pip install thulium[gpu]

Quick Start

from thulium import recognize_image

# Single image recognition
result = recognize_image("document.png", language="en")
print(result.text)

# Batch recognition with confidence scores
from thulium import HTRPipeline

pipeline = HTRPipeline.from_pretrained("thulium-base-multilingual")
results = pipeline.recognize_batch(images, languages=["en", "de", "fr"])

for r in results:
    print(f"{r.text} (confidence: {r.confidence:.2%})")

Supported Languages

52+ languages across 10 scripts (click to expand)

Region	Languages
Western Europe	English, German, French, Spanish, Italian, Portuguese, Dutch
Scandinavia	Swedish, Norwegian, Danish, Finnish, Icelandic
Eastern Europe	Polish, Czech, Hungarian, Romanian, Bulgarian, Ukrainian, Russian
Baltic	Lithuanian, Latvian, Estonian
Caucasus	Georgian, Armenian, Azerbaijani
Middle East	Arabic, Hebrew, Persian, Turkish
South Asia	Hindi, Bengali, Tamil, Telugu, Urdu
East Asia	Chinese, Japanese, Korean

Documentation

Guide	Description
Getting Started	Installation and first steps
API Reference	Complete API documentation
Model Zoo	Pretrained model catalog
Training Guide	Train custom models
Architecture	System design overview

Performance

Benchmarks on IAM Handwriting Database:

Model	CER	WER	Latency
thulium-tiny	5.2%	14.1%	12ms
thulium-base	3.8%	10.2%	28ms
thulium-large	2.9%	7.8%	65ms

Measured on NVIDIA A100, batch size 1, PyTorch 2.0+

Citation

@software{thulium2025,
  title={Thulium: Multilingual Handwriting Recognition},
  author={Thulium Authors},
  year={2025},
  url={https://github.com/thulium-dev/thulium}
}

Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

License

Apache 2.0 — see LICENSE for details.

Release files for thulium-htr 1.2.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for thulium-htr 1.2.1
File	Size	Uploaded
thulium_htr-1.2.1.tar.gz	180.9 kB	Dec 12, 2025	Details

Built distribution (wheel)

Table of built distributions (wheels) for thulium-htr 1.2.1
File	Interpreter	ABI	Platform	Reset
thulium_htr-1.2.1-py3-none-any.whl 175.3 kB Dec 12, 2025	Python 3	none	any	Details

Total release size: 356.2 kB

Release files / thulium_htr-1.2.1.tar.gz

Download URL	thulium_htr-1.2.1.tar.gz
Size	180.9 kB
Tags	Source
SHA-256 checksum How to use checksums	`7be1c631265861726b5223d3d34829ba939ce84c16c7bc619c5be15b42790eee`
BLAKE2b-256 checksum How to use checksums	`bea203338822954f6c60e391a2d1e38fdac7661fb7af3e156325c82b27428dc2`
Upload date	Dec 12, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.14.1`

Release files / thulium_htr-1.2.1-py3-none-any.whl

Download URL	thulium_htr-1.2.1-py3-none-any.whl
Size	175.3 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`2326b9b317d0838d5535057f688f1a0e3403e74c24ad845dac241c710451079e`
BLAKE2b-256 checksum How to use checksums	`a05fb28ee3a1394887cb7d7564991b81be6bc177d77ef5f7bbf0080678b5e37d`
Upload date	Dec 12, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.14.1`