Use the NGC CLI to download:
Copied!
Model
nvCLIP4STR is optical character recognition network, which aims to recognize characters from the images. One pretrained nvCLIP4STR model is delivered, which is trained on 7 dataset with alphanumeric labels. This model is ready for commercial use.
Use the NGC CLI to download:
Copied!
| Field | Response |
|---|---|
| Intended Application(s) & Domain(s): | Recognizing Text in Images |
| Model Type: | Convolutional Neural Network + Transformer Encoder Decoder |
| Intended Users: | The model is intended for developers that build computer vision applications to recognize texts in images. |
| Output: | Text |
| Describe how the model works: | Extracts features from provided images for text. |
| Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: | Not Applicable |
| Technical Limitations: | The model may struggle to identify handwritten texts in images and texts that are more than 80% occluded. |
| Verified to have met prescribed NVIDIA standards: | Yes |
| Performance Metrics: | Accuracy |
| Potential Known Risks: | The model may not recognize texts that are more than 80% occluded. |
| Licensing: | NVIDIA Open Model License |