Downloads · 30 days
7
5% of all-time downloads
nyansapo-ocr-trocr-lora_v1
Nzyoka19/nyansapo-ocr-trocr-lora_v1
nyansapo-ocr-trocr-lora_v1 is a image-to-text model from Nzyoka19. Use it when you need a caption or text from an image. It is set up for peft. The card lists the license as mit.
Fine-tuned OCR model by Nyansapo built on microsoft/trocr-base-handwritten with LoRA adapters on the decoder.
All-time downloads
136
Public
Repo size
20.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors20.1 MB · 86%
At a glance
- Task
- Image-to-Text
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Mar 8, 2026
- Updated
- Mar 8, 2026
- SHA
- d453a21e
Base models
Spaces
Model card
From the Hugging Face model README
Nyansapo OCR — TrOCR LoRA v1
Fine-tuned OCR model by Nyansapo built on microsoft/trocr-base-handwritten
with LoRA adapters on the decoder.
Training details
- Base model: microsoft/trocr-base-handwritten
- PEFT: LoRA (r=16, alpha=32)
- Targets: q_proj, k_proj, v_proj, out_proj, fc1, fc2
- Dataset: Nzyoka19/ocr_images
Inference
from transformers import VisionEncoderDecoderModel, TrOCRProcessor
from peft import PeftModel
from PIL import Image
base = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-base-handwritten')
processor = TrOCRProcessor.from_pretrained('Nzyoka19/nyansapo-ocr-trocr-lora_v1')
base.decoder = PeftModel.from_pretrained(base.decoder, 'Nzyoka19/nyansapo-ocr-trocr-lora_v1')
base.eval()
image = Image.open('image.png').convert('RGB')
pixel_values = processor(images=image, return_tensors='pt').pixel_values
ids = base.generate(pixel_values)
print(processor.batch_decode(ids, skip_special_tokens=True)[0])
- Task
- Image-to-Text
- Library
- peft
- License
- mit
- Languages
- en
- Created
- Mar 8, 2026
- Updated
- Mar 8, 2026