document-understanding
latest
false
- Overview
- Building models
- Consuming models
- ML packages
- 1040 - ML package
- 1040 Schedule C - ML package
- 1040 Schedule D - ML package
- 1040 Schedule E - ML package
- 1040x - ML package
- 3949a - ML package
- 4506T - ML package
- 709 - ML package
- 941x - ML package
- 9465 - ML package
- ACORD131 - ML package
- ACORD140 - ML package
- ACORD25 - ML package
- Bank Statements - ML package
- Bills Of Lading - ML package
- Certificate of Incorporation - ML package
- Certificate of Origin - ML package
- Checks - ML package
- Children Product Certificate - ML package
- CMS 1500 - ML package
- EU Declaration of Conformity - ML package
- Financial Statements - ML package
- FM1003 - ML package
- I9 - ML package
- ID Cards - ML package
- Invoices - ML package
- Invoices Australia - ML package
- Invoices China - ML package
- Invoices Hebrew - ML package
- Invoices India - ML package
- Invoices Japan - ML package
- Invoices Shipping - ML package
- Packing Lists - ML package
- Payslips - ML package
- Passports - ML package
- Purchase Orders - ML package
- Receipts - ML Package
- Remittance Advices - ML package
- UB04 - ML package
- Utility Bills - ML package
- Vehicle Titles - ML package
- W2 - ML package
- W9 - ML package
- Public endpoints
- Supported languages
- Data and security
- Licensing and Charging Logic
- How to
ML models and capabilities
Document Understanding User Guide
ML models and capabilities
All of our models can be trained to understand any language recognized by an OCR. This also applies to languages not immediately recognized by the model. For instance, if you're working with purchase orders in Romanian, you'll need to specifically train the model with Romanian language purchase orders. Check the OCR page for a list of languages supported by our OCR engines.
Important: Exceptions are Chinese, Japanese, Korean and
right-to-left languages. To process documents in these languages, you can only train
them on the out-of-the-box model package specifically designed for that language (like
Invoices China
Invoices Japan). Alternatively, you can use the generic Document
Understanding package.
The following table lists the languages supported out-of-the-box by our models.
ML model or capability | Languages supported out of the box (pre-trained) |
---|---|
709 - Preview | English |
941x - Preview | English |
1040 | English |
1040 Schedule C - Preview | English |
1040 Schedule D - Preview | English |
1040 Schedule E - Preview | English |
1040x - Preview | English |
3949a - Preview | English |
9465 - Preview | English |
4506T | English |
Acord125 | English |
Acord126 | English |
Acord131 | English |
Acord140 | English |
Acord25 | English |
Bank Statements | English |
Bills of Lading |
|
Certificate of Incorporation/ Good Standing | English |
Certificate of Origin | English |
Checks | English |
Children Product Certificate | English |
CMS1500 | English |
EU Declaration of Conformity | English |
Financial Statements | English |
FM1003 - Preview | English |
I9 | English |
IDCards | Trained to
support ID cards and driver's licenses from:
|
Invoices |
|
InvoicesAustralia Note: Deprecated:
model has been merged into the Invoices model. See the Invoices
model page for details.
| English |
Invoices China |
|
Invoices Hebrew - Preview | Hebrew |
Invoices India | English |
Invoices Japan | Japanese |
Invoices Shipping | English |
Packing Lists | English |
Passports | All nationalities |
Pay slips | English |
Purchase Orders |
|
Receipts |
|
RemittanceAdvices | English |
UB04 - ML package - Preview | English |
Utility Bills | English |
Vehicle Titles | English |
W2 | English |
W9 |
|