Skip to content
ModelListedExternal
Download

Donut Base German Receipts

> ⚠️Warning > > - Transformers versions above 4.28.XX may break inference result: > - Latest versions seem to work properly (e.g 4.57.6)

Sourcehuggingface.co/Philipp92/donut-base-german-receipts/tree/f49a756d8c2103c3d57f52c0ea65583a8a0cc907
KindCLIP visionBase modelnaver-clova-ix/donut-baseVersion

Model source

Kind
CLIP vision
File size
772 MB
Base model
naver-clova-ix/donut-base
Version
vmodel
Updated
Sep 25, 2026
Downloads
34
Tasks
Captioning
Source
Hugging Face

Source description

⚠️Warning

Donut German Receipts

Fine-tuned donut model for german receipts.

Model Details

  • Base model: naver-clova-ix/donut-base
  • Dataset:
    • german receipts based on small private dataset(473 images)
  • Training:
    • training based on 435 images
    • test validation with 38 images
      • accurcay on supermarked-receipts is well (~70% exact string comparison)
      • not so many unkown stores in dataset, results differ in quality
    • Image size used: 960x1280
    • Epochs: 3
    • LR: 2e-5
    • Batch-Size: 2

Input Example

bon144

Output Schema

{
  "store": "C & A Geretsried",
  "date": "26.07.2025",
  "address": "Karl-Lederer-Platz 15",
  "total": "39,99"
}

Framework versions

  • Transformers 4.27.4
  • Pytorch 2.7.1
  • Datasets 4.0.0
  • Tokenizers 0.13.3

Sources

1 source
Hugging FacePrimaryVersion f49a756d8c2103c3d57f52c0ea65583a8a0cc907
huggingface.co/Philipp92/donut-base-german-receipts/tree/f49a756d8c2103c3d57f52c0ea65583a8a0cc907

Verified Sep 11

Model artifacts

1 artifact

model.safetensors

safetensors · 772 MB · SHA-256 a07fc0359240…10cb · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 11huggingface.co/Philipp92/donut-base-german-receipts

--- license: mit language: - de base_model: - naver-clova-ix/donut-base pipeline_tag: image-to-text tags: - Transformers - donut - receipts --- > ⚠️**Warning** > > - Transformers versions above 4.28.XX may break inference result: https://github.com/huggingface/transformers/issues/39473 > - Latest versions seem to work properly (e.g 4.57.6) # Donut German Receipts Fine-tuned donut model for german receipts. ## Model Details - Base model: naver-clova-ix/donut-base - Dataset: - german receipts based on small private dataset(473 images) - Training: - training based on 435 images - test validation with 38 images - accurcay on supermarked-receipts is well (~70% exact string comparison) - not so many unkown stores in dataset, results differ in quality - Image size used: 960x1280 - Epochs: 3 - LR: 2e-5 - Batch-Size: 2 ## Input Example ![bon144](https://cdn-uploads.huggingface.co/production/uploads/654b93c97824e2bb58ca3f50/R65uAW7dnD3GuqTlX7J5d.jpeg) ## Output Schema ```json { "store": "C & A Geretsried", "date": "26.07.2025", "address": "Karl-Lederer-Platz 15", "total": "39,99" } ``` ## Framework versions - Transformers 4.27.4 - Pytorch 2.7.1 - Datasets 4.0.0 - Tokenizers 0.13.3

NoteSep 11huggingface.co/Philipp92/donut-base-german-receipts

Source context: 34 downloads · 1 likes · Pipeline image-to-text · Repo Philipp92/donut-base-german-receipts