feat(analyzer): add country-specific predefined recognizer for Taiwan (TW) National ID

bn_test/config.cfg

@@ -0,0 +1,104 @@
+[paths]
+train = null
+dev = null
+vectors = null
+init_tok2vec = null
+
+[system]
+seed = 0
+gpu_allocator = null
+
+[nlp]
+lang = "bn"
+pipeline = []
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+batch_size = 1000
+
+[corpora]
+
+[training]
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+accumulate_gradient = 1
+patience = 1600
+max_epochs = 0
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+annotating_components = []
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+before_to_disk = null
+before_update = null
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[components]
+
+[pretraining]
+
+[nlp.tokenizer]
+@tokenizers = "spacy.Tokenizer.v1"
+
+[nlp.vectors]
+@vectors = "spacy.Vectors.v1"
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+gold_preproc = false
+max_length = 0
+limit = 0
+augmenter = null
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+gold_preproc = false
+max_length = 0
+limit = 0
+augmenter = null
+
+[training.logger]
+@loggers = "spacy.ConsoleLogger.v1"
+progress_bar = false
+
+[training.batcher]
+@batchers = "spacy.batch_by_words.v1"
+discard_oversize = false
+tolerance = 0.2
+get_length = null
+
+[training.optimizer]
+@optimizers = "Adam.v1"
+beta1 = 0.9
+beta2 = 0.999
+L2_is_weight_decay = true
+L2 = 0.01
+grad_clip = 1.0
+use_averages = false
+eps = 1e-08
+learn_rate = 0.001
+
+[training.score_weights]
+
+[initialize.tokenizer]
+
+[initialize.components]
+
+[training.batcher.size]
+@schedules = "compounding.v1"
+start = 100
+stop = 1000
+compound = 1.001
+t = 0.0

bn_test/meta.json

@@ -0,0 +1,31 @@
+{
+  "lang":"bn",
+  "name":"pipeline",
+  "version":"0.0.0",
+  "spacy_version":">=3.8.14,<3.9.0",
+  "description":"",
+  "author":"",
+  "email":"",
+  "url":"",
+  "license":"",
+  "spacy_git_version":"0069cf9",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":null,
+    "mode":"default"
+  },
+  "labels":{
+
+  },
+  "pipeline":[
+
+  ],
+  "components":[
+
+  ],
+  "disabled":[
+
+  ]
+}

bn_test/vocab/key2row

@@ -0,0 +1 @@
+�

bn_test/vocab/lookups.bin

@@ -0,0 +1 @@
+�