Skip to content
ModelListedExternal
Download

Manga Ocr

Full-precision manga-ocr-base repackaged into a single self-consistent repo for ONNX inference — matched weights and tokenizer in one place.

Sourcehuggingface.co/NorwayFish/manga-ocr/tree/c2bdcfd73348753832105d0d79018ee83df8a6a7
KindCLIP visionBase modelkha-white/manga-ocr-baseVersionBgrade

Model source

Kind
CLIP vision
File size
112 MB
Base model
kha-white/manga-ocr-base
Version
vdecoder_model
Updated
Oct 30, 2026
Downloads
19
Source
Hugging Face

Source description

manga-ocr (repackaged, full-precision)

Full-precision manga-ocr-base repackaged into a single self-consistent repo for ONNX inference — matched weights and tokenizer in one place.

  • Weights (encoder_model.onnx 343 MB, decoder_model.onnx 117 MB): the full-precision, non-merged ONNX export (768-dim ViT encoder) from onnx-community/manga-ocr-base-ONNX, itself a transformers.js export of kha-white/manga-ocr-base.
  • Tokenizer (tokenizer.json, vocab.txt, 6144-token WordPiece): verified id→token-identical to the weights' lineage.

I/O: encoder takes pixel_values → hidden states; decoder takes input_ids + encoder_hidden_states → logits (no KV-cache branch).

Sources

1 source
Hugging FacePrimaryVersion c2bdcfd73348753832105d0d79018ee83df8a6a7
huggingface.co/NorwayFish/manga-ocr/tree/c2bdcfd73348753832105d0d79018ee83df8a6a7

Verified Oct 30

Download files

Repository files

File inventory only; completeness is unverified.

Model artifacts

1 artifact

decoder_model.onnx

onnx · 112 MB · SHA-256 a79710e3bc36…50bd · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeAug 14huggingface.co/NorwayFish/manga-ocr

--- license: apache-2.0 base_model: kha-white/manga-ocr-base language: - ja pipeline_tag: image-to-text tags: - onnx - vision-encoder-decoder - image-to-text - manga-ocr --- # manga-ocr (repackaged, full-precision) Full-precision manga-ocr-base repackaged into a single self-consistent repo for ONNX inference — matched weights **and** tokenizer in one place. - **Weights** (`encoder_model.onnx` 343 MB, `decoder_model.onnx` 117 MB): the full-precision, **non-merged** ONNX export (768-dim ViT encoder) from [`onnx-community/manga-ocr-base-ONNX`](https://huggingface.co/onnx-community/manga-ocr-base-ONNX), itself a transformers.js export of [`kha-white/manga-ocr-base`](https://huggingface.co/kha-white/manga-ocr-base). - **Tokenizer** (`tokenizer.json`, `vocab.txt`, 6144-token WordPiece): verified id→token-identical to the weights' lineage. I/O: encoder takes `pixel_values` → hidden states; decoder takes `input_ids` + `encoder_hidden_states` → logits (no KV-cache branch).

NoteOct 30huggingface.co/NorwayFish/manga-ocr

Source context: 19 downloads · 0 likes · Pipeline image-to-text · Repo NorwayFish/manga-ocr

NoteAug 14huggingface.co/NorwayFish/manga-ocr

Source context: 36 downloads · 0 likes · Pipeline image-to-text · Repo NorwayFish/manga-ocr