1 instantiation of BertTokenizer
Microsoft.ML.Tokenizers (1)
Model\BertTokenizer.cs (1)
811
return new
BertTokenizer
(vocab, vocabReverse, options);
38 references to BertTokenizer
Microsoft.ML.Tokenizers (12)
Model\BertTokenizer.cs (12)
653
/// Create a new instance of the <see cref="
BertTokenizer
"/> class.
657
/// <returns>A new instance of the <see cref="
BertTokenizer
"/> class.</returns>
661
public static
BertTokenizer
Create(
669
/// Create a new instance of the <see cref="
BertTokenizer
"/> class.
673
/// <returns>A new instance of the <see cref="
BertTokenizer
"/> class.</returns>
677
public static
BertTokenizer
Create(
683
/// Create a new instance of the <see cref="
BertTokenizer
"/> class asynchronously.
692
public static async Task<
BertTokenizer
> CreateAsync(
708
/// Create a new instance of the <see cref="
BertTokenizer
"/> class asynchronously.
717
public static async Task<
BertTokenizer
> CreateAsync(
734
private static
BertTokenizer
Create(Stream vocabStream, BertOptions? options, bool disposeStream)
756
private static
BertTokenizer
Create(
Microsoft.ML.Tokenizers.Tests (26)
BertTokenizerTests.cs (26)
42
BertTokenizer
[] bertTokenizers = [
BertTokenizer
.Create(vocabFile, bertOptions),
BertTokenizer
.Create(vocabStream, bertOptions)];
44
foreach (
var
tokenizer in bertTokenizers)
113
BertTokenizer
[] bertTokenizers = [
BertTokenizer
.Create(vocabFile),
BertTokenizer
.Create(vocabStream)];
115
foreach (
var
tokenizer in bertTokenizers)
184
BertTokenizer
[] bertTokenizers = [
BertTokenizer
.Create(vocabFile, new BertOptions { LowerCaseBeforeTokenization = false }),
185
BertTokenizer
.Create(vocabStream, new BertOptions { LowerCaseBeforeTokenization = false })];
187
foreach (
var
tokenizer in bertTokenizers)
235
BertTokenizer
bertTokenizer = await
BertTokenizer
.CreateAsync(vocabStream); // lowercasing and no accent stripping
252
bertTokenizer = await
BertTokenizer
.CreateAsync(vocabStream, new BertOptions { LowerCaseBeforeTokenization = false }); // no lowercasing and no accent stripping
267
bertTokenizer = await
BertTokenizer
.CreateAsync(vocabStream, new BertOptions { RemoveNonSpacingMarks = true }); // lowercasing and accent stripping
281
bertTokenizer = await
BertTokenizer
.CreateAsync(vocabStream, new BertOptions { LowerCaseBeforeTokenization = false, RemoveNonSpacingMarks = true }); // no lowercasing and accent stripping
310
BertTokenizer
bertTokenizer = await
BertTokenizer
.CreateAsync(vocabStream); // tokenize Chinese characters
329
bertTokenizer = await
BertTokenizer
.CreateAsync(vocabStream, new BertOptions { IndividuallyTokenizeCjk = false }); // do not tokenize Chinese characters
363
BertTokenizer
bertTokenizer =
BertTokenizer
.Create(vocabFile);
463
BertTokenizer
bertTokenizer =
BertTokenizer
.Create(vocabFile);
556
BertTokenizer
bertTokenizer =
BertTokenizer
.Create(vocabFile);