ModelPrésentéExterne

Trocr Small Handwritten GGUF

Handwritten text recognition model for CrispEmbed. Recognizes handwritten text from cropped text-line images. Outputs mixed-case text (unlike trocr-small-printed which uppercases).

Sourcehuggingface.co/cstr/trocr-small-handwritten-GGUF/tree/24a118e60533478cd385b581aa9b272210086286

TypeModèleModèle de basemicrosoft/trocr-small-handwrittenVersionRevision 24a118eBClasse

Source du modèle

Type: Modèle
Taille du fichier: 64,4–119 MB
Modèle de base: microsoft/trocr-small-handwritten
Version: vRevision 24a118e
Mis à jour: 30 oct. 2026
Téléchargements: 97
Source: Hugging Face

Description de la source

TrOCR-small Handwritten Text — GGUF

Handwritten text recognition model for CrispEmbed. Recognizes handwritten text from cropped text-line images. Outputs mixed-case text (unlike trocr-small-printed which uppercases).

Architecture: DeiT-small encoder (12L, 384d, 6 heads) + TrOCR decoder (6L, 256d, 8 heads). XLM-R vocabulary (64,044 tokens). 61M parameters.

Source: microsoft/trocr-small-handwritten (MIT).

Model Variants

Variant	Size	Recognition quality
F32	235 MB	exact token match vs HuggingFace (greedy)
F16	118 MB	identical to F32
Q8_0	63 MB	identical to F32

Q4_K not provided — 256d decoder bottleneck is too narrow for 4-bit quantization.

Usage

# Single crop recognition
crispembed -m trocr-small-handwritten-q8_0.gguf --ocr crop.png

# Full pipeline with DBNet detection
crispembed --det dbnet-ic15-q4_k.gguf -m trocr-small-handwritten-q8_0.gguf --ocr scan.png

License

MIT (same as microsoft/trocr-small-handwritten).

Provenance and EU AI Act Art. 53 note

Upstream model: microsoft/trocr-small-handwritten — published by microsoft.
Upstream licence: mit. This repository redistributes under the same terms; it grants no rights the upstream licence does not.
What was done here: format conversion and/or quantisation only (GGUF). No training, no fine-tuning, no merging, no distillation, no change to architecture, vocabulary or capability. Only the numeric representation of the upstream weights differs.
Training data: documented — where it is documented at all — by the upstream provider; see the upstream model card. No training data was used, added or selected by this repository. No training-content summary was found on the upstream model card at the time of writing; that documentation gap is upstream's and is not filled here.
Provider status: under Regulation (EU) 2024/1689 the upstream authors remain the provider of this model. Converting the serialisation format does not make this repository the provider of a new general-purpose AI model, and no such claim is made. Questions about training content, copyright policy or model capability belong upstream.

Sources

1 source

Hugging FacePrincipalVersion 24a118e60533478cd385b581aa9b272210086286

huggingface.co/cstr/trocr-small-handwritten-GGUF/tree/24a118e60533478cd385b581aa9b272210086286

Vérifié 30 oct.

Download files

Repository files

File inventory only; completeness is unverified.

Artefacts du modèle

2 artefacts

trocr-small-handwritten-f16.gguf

gguf · 119 MB · SHA-256 50e9179cbcb7…415f · Hugging Face

Download file

trocr-small-handwritten-q8_0.gguf

gguf · 64,4 MB · SHA-256 b91b684fe6a7…471f · Hugging Face

Download file

Extraits de sources

3 extraits

Readme14 aoûthuggingface.co/cstr/trocr-small-handwritten-GGUF

--- license: mit language: - en tags: - text-recognition - ocr - trocr - handwriting - gguf - crispembed base_model: microsoft/trocr-small-handwritten pipeline_tag: image-to-text --- # TrOCR-small Handwritten Text — GGUF Handwritten text recognition model for [CrispEmbed](https://github.com/CrispStrobe/CrispEmbed). Recognizes handwritten text from cropped text-line images. Outputs **mixed-case** text (unlike trocr-small-printed which uppercases). **Architecture**: DeiT-small encoder (12L, 384d, 6 heads) + TrOCR decoder (6L, 256d, 8 heads). XLM-R vocabulary (64,044 tokens). 61M parameters. **Source**: [microsoft/trocr-small-handwritten](https://huggingface.co/microsoft/trocr-small-handwritten) (MIT). ## Model Variants | Variant | Size | Recognition quality | |---------|------|-------------------| | F32 | 235 MB | exact token match vs HuggingFace (greedy) | | F16 | 118 MB | identical to F32 | | **Q8_0** | **63 MB** | **identical to F32** | Q4_K not provided — 256d decoder bottleneck is too narrow for 4-bit quantization. ## Usage ```bash # Single crop recognition crispembed -m trocr-small-handwritten-q8_0.gguf --ocr crop.png # Full pipeline with DBNet detection crispembed --det dbnet-ic15-q4_k.gguf -m trocr-small-handwritten-q8_0.gguf --ocr scan.png ``` ## License MIT (same as [microsoft/trocr-small-handwritten](https://huggingface.co/microsoft/trocr-small-handwritten)). ## Provenance and EU AI Act Art. 53 note - **Upstream model:** [microsoft/trocr-small-handwritten](https://huggingface.co/microsoft/trocr-small-handwritten) — published by `microsoft`. - **Upstream licence:** `mit`. This repository redistributes under the same terms; it grants no rights the upstream licence does not. - **What was done here:** format conversion and/or quantisation only (GGUF). No training, no fine-tuning, no merging, no distillation, no change to architecture, vocabulary or capability. Only the numeric representation of the upstream weights differs. - **Training data:** documented — where it is documented at all — by the upstream provider; see the upstream model card. No training data was used, added or selected by this repository. No training-content summary was found on the upstream model card at the time of writing; that documentation gap is upstream's and is not filled here. - **Provider status:** under Regulation (EU) 2024/1689 the upstream authors remain t...

Note30 oct.huggingface.co/cstr/trocr-small-handwritten-GGUF

Source context: 97 downloads · 1 likes · Pipeline image-to-text · Repo cstr/trocr-small-handwritten-GGUF

Note14 aoûthuggingface.co/cstr/trocr-small-handwritten-GGUF

Source context: 123 downloads · 0 likes · Pipeline image-to-text · Repo cstr/trocr-small-handwritten-GGUF