Manga Ocr Finetuned
ONNX export of JustANormalTinkerer/manga-ocr-finetuned — a finetuned manga-OCR with a distilled 192-dim ViT encoder (the upstream ships PyTorch only).
Source du modèle
- Type
- CLIP vision
- Taille du fichier
- 113 MB
- Modèle de base
- JustANormalTinkerer/manga-ocr-finetuned
- Version
- vdecoder_model
- Mis à jour
- 30 oct. 2026
- Téléchargements
- 4
- Source
- Hugging Face
Description de la source
manga-ocr-finetuned (ONNX)
ONNX export of JustANormalTinkerer/manga-ocr-finetuned
— a finetuned manga-OCR with a distilled 192-dim ViT encoder (the upstream
ships PyTorch only).
- Weights:
encoder_model.onnx(22 MB, 192-dim encoder) +decoder_model.onnx(118 MB, non-merged), exported withoptimum. I/O: encoderpixel_values→last_hidden_state; decoderinput_ids+encoder_hidden_states→logits. - Tokenizer: the manga-ocr 6144-token WordPiece
tokenizer.json, verified vocab-identical to this model's lineage.
Repackaged for single-repo, self-consistent ONNX inference.
Sources
1 source
Sources
1 sourceVérifié 30 oct.
Download files
Repository files
File inventory only; completeness is unverified.
Artefacts du modèle
1 artefact
Artefacts du modèle
1 artefactExtraits de sources
3 extraits
Extraits de sources
3 extraits--- license: apache-2.0 base_model: JustANormalTinkerer/manga-ocr-finetuned language: - ja pipeline_tag: image-to-text tags: - onnx - vision-encoder-decoder - image-to-text - manga-ocr --- # manga-ocr-finetuned (ONNX) ONNX export of [`JustANormalTinkerer/manga-ocr-finetuned`](https://huggingface.co/JustANormalTinkerer/manga-ocr-finetuned) — a finetuned manga-OCR with a distilled **192-dim** ViT encoder (the upstream ships PyTorch only). - **Weights**: `encoder_model.onnx` (22 MB, 192-dim encoder) + `decoder_model.onnx` (118 MB, non-merged), exported with `optimum`. I/O: encoder `pixel_values` → `last_hidden_state`; decoder `input_ids` + `encoder_hidden_states` → `logits`. - **Tokenizer**: the manga-ocr 6144-token WordPiece `tokenizer.json`, verified vocab-identical to this model's lineage. Repackaged for single-repo, self-consistent ONNX inference.
Source context: 4 downloads · 0 likes · Pipeline image-to-text · Repo NorwayFish/manga-ocr-finetuned
Source context: 10 downloads · 0 likes · Pipeline image-to-text · Repo NorwayFish/manga-ocr-finetuned
