GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
VietAlphaLabs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
VietAlphaLabs
Model Tree
PaddlePaddle/PaddleOCR-VL-1.6
Input Modalities
Output Modalities
Supported Functionality
For direct OCR recognition:
bash
pip install "transformers>=5.0.0" torch pillow
python
from PIL import Imageimport torchfrom transformers import AutoProcessor, AutoModelForImageTextToTextmodel_id = "VietAlphaLabs/SenOCR-Vi"image_path = "document.png"device = "cuda" if torch.cuda.is_available() else "cpu"model = (AutoModelForImageTextToText.from_pretrained(model_id, torch_dtype=torch.float32).to(device).eval())processor = AutoProcessor.from_pretrained(model_id)image = Image.open(image_path).convert("RGB")messages = [{"role": "user","content": [{"type": "image", "image": image},{"type": "text", "text": "OCR:"},],}]inputs = processor.apply_chat_template(messages,add_generation_prompt=True,tokenize=True,return_dict=True,return_tensors="pt",).to(device)outputs = model.generate(**inputs, max_new_tokens=512)text = processor.decode(outputs[0][inputs["input_ids"].shape[-1]:-1])print(text)
[!NOTE] The qualified benchmark artifact was served in FP32. Lower-precision deployment should be validated separately for the target environment.
For page-level document parsing, use SenOCR-Vi as the VLM recognition model inside the PaddleOCR-VL 1.6 pipeline.
Install the appropriate PaddlePaddle build for the target system, then:
bash
pip install -U "paddleocr[doc-parser]>=3.6.0" huggingface_hub
python
from pathlib import Pathfrom huggingface_hub import snapshot_downloadfrom paddleocr import PaddleOCRVLmodel_dir = snapshot_download(repo_id="VietAlphaLabs/SenOCR-Vi")output_dir = Path("./output")output_dir.mkdir(parents=True, exist_ok=True)pipeline = PaddleOCRVL(pipeline_version="v1.6",vl_rec_model_dir=model_dir,)output = pipeline.predict("document.png")for result in output:result.print()result.save_to_json(save_path=output_dir)result.save_to_markdown(save_path=output_dir)
PaddleOCR-VL also supports PDF input, layout analysis, document restructuring, and optimized serving backends. See the PaddleOCR-VL documentation.
shell
hf download VietAlphaLabs/SenOCR-Vi --local-dir SenOCR-Vi/
SenOCR-Vi is evaluated on the corrected Vietnamese page population used for the MDPBench document-parsing comparison.
| Model | Parameters | Vietnamese composite |
|---|---|---|
| chandra-ocr-2 | 5B | 85.60 |
| MonkeyOCRv2-B-Parsing | 0.7B | 83.20 |
| Claude-Sonnet-4.6 | Undisclosed | 83.10 |
| SenOCR-Vi | 0.959B | 82.83 |
| ChatGPT-5.2-2025-12-11 | Undisclosed | 82.10 |
| PaddleOCR-VL-1.6 |
External model scores are taken from the MDPBench official leaderboard. Public parameter counts are shown where available; Claude-Sonnet-4.6 and ChatGPT-5.2 do not disclose model size.
At 0.959B parameters, SenOCR-Vi is 0.27 points behind Claude-Sonnet-4.6, 0.73 points ahead of ChatGPT-5.2, and 1.93 points ahead of PaddleOCR-VL-1.6 on Vietnamese. chandra-ocr-2 scores 2.77 points higher at 5B parameters, about 5.2 times SenOCR-Vi's parameter count.
On the 160-page Vietnamese slice:
| Metric | SenOCR-Vi |
|---|---|
Page-level text_block Edit_dist | 0.13305 |
1 - Edit_dist | 86.7% |
The 86.7% figure is a Vietnamese text-recognition score under 1 - Edit_dist; the 82.83 document composite also includes structured document elements.
On the controlled English/Vietnamese/Simplified Chinese population:
| Condition | Composite |
|---|---|
| Digital documents | 91.1 |
| Photographed documents | 80.8 |
SenOCR-Vi remains usable outside Vietnamese, although multilingual aggregate performance is not the primary optimization target.
| Language | Composite |
|---|---|
| English | 82.08 |
| Vietnamese | 82.83 |
| Simplified Chinese | 84.03 |
| EN/VI/ZH macro | 82.98 |
For comparison, PaddleOCR-VL-1.6 records an EN/VI/ZH macro of 83.43 from the corresponding MDPBench language columns.
SenOCR-Vi scores are re-aggregated over the actual evaluation-page population.
The original project scorer emitted three additional non-page rows because of a documented key-parsing defect. All three affected the Vietnamese population. Removing those phantom rows gives the reported 82.83 Vietnamese composite.
The 82.98 EN/VI/ZH macro is a three-language summary only. It is not the full MDPBench overall score.
SenOCR-Vi was initialized as a fresh decoder-only LoRA fine-tune of PaddleOCR-VL-1.6.
| Setting | Value |
|---|---|
| Base model | PaddlePaddle/PaddleOCR-VL-1.6 |
| Total parameters | 958,588,736 |
| Trainable parameters | 12,091,392 |
| Trainable share | 1.2614% |
| LoRA rank | 32 |
| LoRA alpha | 64 |
| LoRA scaling | 2.0 |
| Decoder projections | 126 |
| Training records | 42,254 |
The vision encoder, vision-language aligner/projector, embeddings, and LM head remained frozen.
LoRA was applied to seven projections in each of 18 decoder layers:
q_projk_projv_projo_projgate_projup_projdown_projThe final adapter was merged into the base weights in FP32. Merge-equivalence validation produced 128/128 exact decoded matches between base-plus-adapter inference and the merged model.
The training corpus contains 42,254 OCR records and 1,171,860 supervised target tokens per corpus pass.
| Corpus lane | Records | Target tokens |
|---|---|---|
| Vietnamese handwriting (Viet-Handwriting-OCR-v2) | 23,046 | 456,066 |
| VinText | 10,174 | 32,531 |
| Vietnamese text corpus | 1,539 | 491,846 |
| General OCR replay | 4,687 | 22,594 |
| Private archival corpus | 2,808 | 168,823 |
The corpus is Vietnamese-dominant, with handwriting, scene/document text, longer-form printed Vietnamese, general OCR replay, and restricted archival material. The Vietnamese handwriting lane is sourced from 5CD-AI/Viet-Handwriting-OCR-v2.
Restricted archival source material is not redistributed with SenOCR-Vi. Public datasets retain their original licensing terms.
SenOCR-Vi is optimized primarily for Vietnamese text recognition.
Structured elements remain more difficult than ordinary text on the controlled evaluation population:
| Component | Score |
|---|---|
| Text | 86.5% under 1 - NED |
| Table | 70.7 TEDS |
| Formula | 72.5 CDM |
The model is therefore not positioned as a table- or formula-specialized OCR system.
Other difficult cases include:
No controlled production benchmark has yet established pages per second, optimized BF16 peak VRAM, or latency relative to other OCR systems.
For legal, financial, historical, or otherwise high-stakes transcription, human review is recommended.
SenOCR-Vi is released under the Apache License 2.0.
The model is built on PaddleOCR-VL-1.6, which is also distributed under Apache 2.0.
Dataset licenses vary by source. Restricted archival material is not included in the release.
bibtex
@misc{vietalphalab2026senocrvi,title={SenOCR-Vi: A Vietnamese-Specialized Document OCR Model},author={VietAlpha Lab},year={2026},publisher={Hugging Face},url={https://huggingface.co/VietAlphaLabs/SenOCR-Vi},}
| ~0.9B |
| 80.90 |
| Target tokens per pass | 1,171,860 |
| Effective corpus passes | 3.000521 |
| Target-token exposures | ~3.516M |
| Optimizer steps | 1,981 |
| Effective batch size | 64 |
| Maximum sequence length | 4,096 |
| Peak learning rate | 1e-4 |
| Minimum learning rate | 1e-5 |
| Warmup | 3% |
| Weight decay | 0.01 |
| Gradient clipping | 1.0 |
| Training precision | BF16 |
| Final reported train loss | 0.4991 |
| Hardware | 1 x NVIDIA A10G |
| Runtime | 7,266.56 s, ~2 h 01 m |
| Total | 42,254 | 1,171,860 |