TokenizerResult Class
Definition
Important
Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.
The Encoding represents the output of a Tokenizer.
public sealed class TokenizerResulttype TokenizerResult = classPublic NotInheritable Class TokenizerResult- Inheritance
-
TokenizerResult
Constructors
| TokenizerResult(String, String, IReadOnlyList<Split>, Boolean) |
Create a new object of the TokenizerResult object. |
Properties
| Ids |
Gets list of the tokens Ids. The Ids are the main input to a Language Model. They are the token indices, the numerical representations that a LM understands. |
| NormalizedString |
Gets the normalized form of the original string. |
| Offsets |
Gets The list of offsets. These offsets let’s you slice the input string, and thus retrieve the original part that led to producing the corresponding token. |
| OffsetsMappedToOriginalString |
Gets the normalized form of the original string. |
| OriginalString |
Gets the original tokenized string. |
| Tokens |
Gets the generated tokens. They are the string representation of the Ids. |