ModelPublicadoExterno

Manga Ocr

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

Fuentehuggingface.co/NorwayFish/manga-ocr/tree/c2bdcfd73348753832105d0d79018ee83df8a6a7

TipoCLIP visionModelo basekha-white/manga-ocr-baseVersiónBcalidad

Fuente del modelo

Tipo: CLIP vision
Tamaño del archivo: 112 MB
Modelo base: kha-white/manga-ocr-base
Versión: vdecoder_model
Actualizado: 30 oct 2026
Descargas: 19
Fuente: Hugging Face

Descripción de la fuente

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).

Fuentes

1 fuente

Hugging FacePrincipalVersión c2bdcfd73348753832105d0d79018ee83df8a6a7

huggingface.co/NorwayFish/manga-ocr/tree/c2bdcfd73348753832105d0d79018ee83df8a6a7

Verificado 30 oct

Download files

Repository files

File inventory only; completeness is unverified.

Artefactos del modelo

1 artefacto

decoder_model.onnx

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

Download file

Extractos de fuentes

3 extractos

Readme14 agohuggingface.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).

Note30 octhuggingface.co/NorwayFish/manga-ocr

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

Note14 agohuggingface.co/NorwayFish/manga-ocr

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