Update spaCy pipeline

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+ner/model filter=lfs diff=lfs merge=lfs -text
+transformer/model filter=lfs diff=lfs merge=lfs -text
+vi_ner_task-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,30 @@
+---
+tags:
+- spacy
+- token-classification
+language:
+- vi
+---
+| Feature | Description |
+| --- | --- |
+| **Name** | `vi_ner_task` |
+| **Version** | `0.0.0` |
+| **spaCy** | `>=3.7.5,<3.8.0` |
+| **Default Pipeline** | `transformer`, `ner` |
+| **Components** | `transformer`, `ner` |
+| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
+| **Sources** | n/a |
+| **License** | n/a |
+| **Author** | [n/a]() |
+
+### Label Scheme
+
+<details>
+
+<summary>View label scheme (3 labels for 1 components)</summary>
+
+| Component | Labels |
+| --- | --- |
+| **`ner`** | `DATE`, `TASK`, `TIME` |
+
+</details>

config.cfg

@@ -0,0 +1,155 @@
+[paths]
+train = null
+dev = null
+vectors = null
+init_tok2vec = null
+
+[system]
+seed = 0
+gpu_allocator = null
+
+[nlp]
+lang = "vi"
+pipeline = ["transformer","ner"]
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+batch_size = 1000
+vectors = {"@vectors":"spacy.Vectors.v1"}
+
+[nlp.tokenizer]
+@tokenizers = "spacy.vi.VietnameseTokenizer"
+use_pyvi = true
+
+[components]
+
+[components.ner]
+factory = "ner"
+incorrect_spans_key = null
+moves = null
+scorer = {"@scorers":"spacy.ner_scorer.v1"}
+update_with_oracle_cut_size = 100
+
+[components.ner.model]
+@architectures = "spacy.TransitionBasedParser.v2"
+state_type = "ner"
+extra_state_tokens = false
+hidden_width = 64
+maxout_pieces = 2
+use_upper = true
+nO = null
+
+[components.ner.model.tok2vec]
+@architectures = "spacy.HashEmbedCNN.v2"
+pretrained_vectors = null
+width = 96
+depth = 4
+embed_size = 2000
+window_size = 1
+maxout_pieces = 3
+subword_features = true
+
+[components.transformer]
+factory = "transformer"
+max_batch_items = 4096
+set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
+
+[components.transformer.model]
+@architectures = "spacy-transformers.TransformerModel.v3"
+name = "vinai/phobert-base"
+mixed_precision = false
+
+[components.transformer.model.get_spans]
+@span_getters = "spacy-transformers.strided_spans.v1"
+window = 128
+stride = 96
+
+[components.transformer.model.grad_scaler_config]
+
+[components.transformer.model.tokenizer_config]
+use_fast = true
+
+[components.transformer.model.transformer_config]
+
+[corpora]
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+gold_preproc = false
+max_length = 0
+limit = 0
+augmenter = null
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+gold_preproc = false
+max_length = 0
+limit = 0
+augmenter = null
+
+[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
+
+[training.batcher]
+@batchers = "spacy.batch_by_words.v1"
+discard_oversize = false
+tolerance = 0.2
+get_length = null
+
+[training.batcher.size]
+@schedules = "compounding.v1"
+start = 100
+stop = 1000
+compound = 1.001
+t = 0.0
+
+[training.logger]
+@loggers = "spacy.ConsoleLogger.v1"
+progress_bar = false
+
+[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 = 0.00000001
+learn_rate = 0.001
+
+[training.score_weights]
+ents_f = 1.0
+ents_p = 0.0
+ents_r = 0.0
+ents_per_type = null
+
+[pretraining]
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[initialize.components]
+
+[initialize.tokenizer]

meta.json

@@ -0,0 +1,42 @@
+{
+  "lang":"vi",
+  "name":"ner_task",
+  "version":"0.0.0",
+  "description":"",
+  "author":"",
+  "email":"",
+  "url":"",
+  "license":"",
+  "spacy_version":">=3.7.5,<3.8.0",
+  "spacy_git_version":"a6d0fc360",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":null
+  },
+  "labels":{
+    "transformer":[
+
+    ],
+    "ner":[
+      "DATE",
+      "TASK",
+      "TIME"
+    ]
+  },
+  "pipeline":[
+    "transformer",
+    "ner"
+  ],
+  "components":[
+    "transformer",
+    "ner"
+  ],
+  "disabled":[
+
+  ],
+  "requirements":[
+    "spacy-transformers>=1.3.9,<1.4.0"
+  ]
+}

ner/cfg

@@ -0,0 +1,13 @@
+{
+  "moves":null,
+  "update_with_oracle_cut_size":100,
+  "multitasks":[
+
+  ],
+  "min_action_freq":1,
+  "learn_tokens":false,
+  "beam_width":1,
+  "beam_density":0.0,
+  "beam_update_prob":0.0,
+  "incorrect_spans_key":null
+}

ner/moves

@@ -0,0 +1 @@
+��moves٨{"0":{},"1":{"DATE":-1,"TIME":-2,"TASK":-3},"2":{"DATE":-1,"TIME":-2,"TASK":-3},"3":{"DATE":-1,"TIME":-2,"TASK":-3},"4":{"":1,"DATE":-1,"TIME":-2,"TASK":-3},"5":{"":1}}�cfg��neg_key�

tokenizer/cfg

@@ -0,0 +1 @@
+{"use_pyvi":true}

transformer/cfg

@@ -0,0 +1,3 @@
+{
+  "max_batch_items":4096
+}

vocab/key2row

@@ -0,0 +1 @@
+�

vocab/strings.json

@@ -0,0 +1,736 @@
+[
+  " Ba",
+  " T\u01b0",
+  " ba",
+  " t\u01b0",
+  "/10",
+  "/11",
+  "/12",
+  "0/1",
+  "0/9",
+  "1",
+  "1/10",
+  "1/12",
+  "10",
+  "10/10",
+  "10/11",
+  "10h",
+  "11",
+  "11h30",
+  "12/10",
+  "14",
+  "14h",
+  "15",
+  "15/10",
+  "15/11",
+  "17",
+  "17/10",
+  "18h",
+  "2",
+  "2/1",
+  "2/10",
+  "20/1",
+  "20/10",
+  "20/11",
+  "20/12",
+  "20h",
+  "23/12",
+  "23h59",
+  "25/10",
+  "25/11",
+  "3",
+  "3/10",
+  "30",
+  "30/10",
+  "30/11",
+  "30/12",
+  "30/9",
+  "4",
+  "4h",
+  "5",
+  "5h",
+  "6",
+  "7",
+  "7h",
+  "8",
+  "8h",
+  "9",
+  "9h",
+  "A",
+  "AI",
+  "An",
+  "Anh",
+  "B",
+  "Ba",
+  "Backend",
+  "B\u00e1ch",
+  "B\u00ecnh",
+  "B\u1ea3y",
+  "B\u1ec7nh",
+  "C",
+  "Chi\u1ec1u",
+  "Ch\u00fang",
+  "Ch\u01a1i",
+  "Ch\u1ecb",
+  "Ch\u1ee7",
+  "Ch\u1ee7 Nh\u1eadt",
+  "Ch\u1ee7 nh\u1eadt",
+  "Cu\u1ed1i",
+  "C\u01b0\u1eddng",
+  "C\u1ea3",
+  "D",
+  "Data",
+  "Design",
+  "Dev",
+  "DevOps",
+  "Dung",
+  "D\u0169ng",
+  "D\u1ecdn",
+  "F",
+  "FPT",
+  "Frontend",
+  "G",
+  "G\u00f2n",
+  "H",
+  "Hai",
+  "Hoa",
+  "Ho\u00e0n",
+  "Ho\u00e0ng",
+  "Ho\u00e1",
+  "Huy",
+  "H\u00e0",
+  "H\u00f3a",
+  "H\u00f4m",
+  "H\u00f9ng",
+  "H\u01b0ng",
+  "H\u1ea1nh",
+  "H\u1ea3i",
+  "H\u1ecdc",
+  "K",
+  "Khoa",
+  "Kh\u1ea3i",
+  "L",
+  "Lan",
+  "Linh",
+  "L\u00e0m",
+  "L\u00e2m",
+  "L\u1ea1t",
+  "L\u1ecbch",
+  "M",
+  "Mai",
+  "Marketing",
+  "Minh",
+  "Mobile",
+  "M\u00f9ng",
+  "M\u1ed1t",
+  "N",
+  "Nam",
+  "Nghe",
+  "Ng\u00e0y",
+  "Ng\u1ecdc",
+  "Ng\u1eef",
+  "Nh\u00f3m",
+  "Nh\u1eadt",
+  "N\u0103m",
+  "N\u1ea5u",
+  "N\u1eb5ng",
+  "N\u1ed9i",
+  "Ops",
+  "P",
+  "Ph\u00e1p",
+  "Ph\u00f2ng",
+  "Ph\u00fac",
+  "Ph\u01b0\u01a1ng",
+  "Product",
+  "Q",
+  "QA",
+  "Qu\u00e2n",
+  "ROOT",
+  "S",
+  "Sinh",
+  "S\u00e0i",
+  "S\u00e1ng",
+  "S\u00e1u",
+  "S\u1eafp",
+  "S\u1ebfp",
+  "T",
+  "TASK",
+  "Team",
+  "Th\u00e1ng",
+  "Th\u1ea3o",
+  "Th\u1eafng",
+  "Th\u1ee9",
+  "Th\u1ee9 3",
+  "Th\u1ee9 Ba",
+  "Th\u1ee9 B\u1ea3y",
+  "Th\u1ee9 Hai",
+  "Th\u1ee9 N\u0103m",
+  "Th\u1ee9 S\u00e1u",
+  "Th\u1ee9 T\u01b0",
+  "Th\u1ee9 ba",
+  "Th\u1ee9 b\u1ea3y",
+  "Th\u1ee9 hai",
+  "Th\u1ee9 n\u0103m",
+  "Th\u1ee9 s\u00e1u",
+  "Th\u1ee9 t\u01b0",
+  "Tin",
+  "Ti\u1ebfng",
+  "To\u00e1n",
+  "Tr\u00e2m",
+  "Tr\u01b0a",
+  "Tu\u1ea5n",
+  "Tu\u1ea7n",
+  "T\u00e0u",
+  "T\u00f4i",
+  "T\u01b0",
+  "T\u1eadp",
+  "T\u1ed1i",
+  "V",
+  "Vi\u1ebft",
+  "Vi\u1ec7t",
+  "V\u0103n",
+  "V\u0169ng",
+  "V\u1eadt",
+  "XX",
+  "XXX",
+  "Xem",
+  "Xx",
+  "Xxx",
+  "Xxx Xx",
+  "Xxx Xxx",
+  "Xxx Xxxx",
+  "Xxx d",
+  "Xxx xx",
+  "Xxx xxx",
+  "Xxx xxxx",
+  "XxxXxx",
+  "Xxxx",
+  "Xxxxx",
+  "a",
+  "ai",
+  "ail",
+  "all",
+  "ame",
+  "an",
+  "anh",
+  "ase",
+  "ask",
+  "assignment",
+  "ata",
+  "auth",
+  "b",
+  "ba",
+  "backend",
+  "banh",
+  "bug",
+  "bu\u1ed5i",
+  "b\u00e0i",
+  "b\u00e1ch",
+  "b\u00e1o",
+  "b\u00e8",
+  "b\u00ecnh",
+  "b\u00f3ng",
+  "b\u1ea1n",
+  "b\u1ea3n",
+  "b\u1ea3y",
+  "b\u1eaft",
+  "b\u1ec7nh",
+  "b\u1ecb",
+  "b\u1ed9",
+  "c",
+  "call",
+  "cao",
+  "chi\u1ec1u",
+  "cho",
+  "chuy\u1ec1n",
+  "chu\u1ea9n",
+  "ch\u00ednh",
+  "ch\u00fang",
+  "ch\u01a1i",
+  "ch\u1ea1y",
+  "ch\u1ecb",
+  "ch\u1ee3",
+  "ch\u1ee7",
+  "ch\u1ee7 nh\u1eadt",
+  "ch\u1ee9c",
+  "code",
+  "con",
+  "concert",
+  "cu\u1ed1i",
+  "c\u00e0",
+  "c\u00e1",
+  "c\u00e1o",
+  "c\u00f3",
+  "c\u00f4",
+  "c\u00f4ng",
+  "c\u00f9ng",
+  "c\u0169",
+  "c\u01a1m",
+  "c\u01b0\u1edbi",
+  "c\u01b0\u1eddng",
+  "c\u1ea3",
+  "c\u1ea7n",
+  "c\u1eadp",
+  "d",
+  "d/d",
+  "d/dd",
+  "data",
+  "database",
+  "dd",
+  "dd/d",
+  "dd/dd",
+  "ddx",
+  "ddxdd",
+  "deo",
+  "deploy",
+  "design",
+  "dev",
+  "devops",
+  "du",
+  "dung",
+  "dx",
+  "d\u0169ng",
+  "d\u1ea1o",
+  "d\u1eabn",
+  "d\u1eb9p",
+  "d\u1ecdn",
+  "d\u1ee5c",
+  "d\u1ee5ng",
+  "d\u1ef1",
+  "e",
+  "eam",
+  "email",
+  "end",
+  "ent",
+  "ert",
+  "est",
+  "f",
+  "fix",
+  "fpt",
+  "frontend",
+  "g",
+  "game",
+  "ghe",
+  "gia",
+  "gi\u00e1o",
+  "gi\u00e3n",
+  "gi\u1ea3ng",
+  "gi\u1edd",
+  "guitar",
+  "gym",
+  "g\u00e0y",
+  "g\u00f2n",
+  "g\u1eb7p",
+  "g\u1ecdc",
+  "g\u1ecdi",
+  "g\u1eedi",
+  "h",
+  "h30",
+  "h59",
+  "hai",
+  "ham",
+  "him",
+  "hoa",
+  "hop",
+  "ho\u00e0n",
+  "ho\u00e0ng",
+  "ho\u00e1",
+  "ho\u1ea1ch",
+  "ho\u1ea1t",
+  "huy",
+  "h\u00e0",
+  "h\u00e0ng",
+  "h\u00e1m",
+  "h\u00e1p",
+  "h\u00e2n",
+  "h\u00eam",
+  "h\u00ecnh",
+  "h\u00f3a",
+  "h\u00f3m",
+  "h\u00f4m",
+  "h\u00f9ng",
+  "h\u00fac",
+  "h\u00fat",
+  "h\u01a1i",
+  "h\u01b0ng",
+  "h\u01b0\u1edbng",
+  "h\u1ea1c",
+  "h\u1ea1nh",
+  "h\u1ea1y",
+  "h\u1ea3i",
+  "h\u1ea3o",
+  "h\u1ea7u",
+  "h\u1ea9m",
+  "h\u1eadt",
+  "h\u1eafn",
+  "h\u1ebft",
+  "h\u1ec7",
+  "h\u1ecdc",
+  "h\u1ecdp",
+  "h\u1ecfe",
+  "h\u1ed3",
+  "h\u1ee9c",
+  "h\u1ef1c",
+  "ide",
+  "iew",
+  "ign",
+  "ile",
+  "ine",
+  "ing",
+  "inh",
+  "int",
+  "ive",
+  "i\u00e1o",
+  "i\u00e3n",
+  "i\u00ean",
+  "i\u00eau",
+  "i\u1ebft",
+  "i\u1ec1n",
+  "i\u1ec1u",
+  "i\u1ec3m",
+  "i\u1ec3n",
+  "i\u1ec3u",
+  "i\u1ec7c",
+  "i\u1ec7m",
+  "i\u1ec7n",
+  "i\u1ec7p",
+  "i\u1ec7t",
+  "i\u1ec7u",
+  "k",
+  "khai",
+  "khi",
+  "khoa",
+  "kh\u00e1ch",
+  "kh\u00e1m",
+  "kh\u1ea3i",
+  "kh\u1ea3o",
+  "kh\u1ecfe",
+  "kia",
+  "ki\u1ec3m",
+  "k\u00fd",
+  "k\u1ebf",
+  "k\u1ef9",
+  "l",
+  "lan",
+  "linh",
+  "live",
+  "li\u1ec7u",
+  "loy",
+  "luy\u1ec7n",
+  "lu\u1eadn",
+  "l\u00e0m",
+  "l\u00e2m",
+  "l\u00fac",
+  "l\u00fd",
+  "l\u1ea1i",
+  "l\u1ea1t",
+  "l\u1eadp",
+  "l\u1ecbch",
+  "l\u1ed7i",
+  "m",
+  "mai",
+  "mail",
+  "marketing",
+  "minh",
+  "mobile",
+  "module",
+  "mua",
+  "mu\u1ed1n",
+  "m\u00f4n",
+  "m\u00f9ng",
+  "m\u1eb9",
+  "m\u1ec1m",
+  "m\u1ed1t",
+  "m\u1ed7i",
+  "m\u1edbi",
+  "n",
+  "nam",
+  "nay",
+  "nghe",
+  "nghi\u1ec7m",
+  "nghi\u1ec7p",
+  "ngo\u00e0i",
+  "ng\u00e0y",
+  "ng\u1ecdc",
+  "ng\u1ee7",
+  "ng\u1eef",
+  "nh\u00e0",
+  "nh\u00e2n",
+  "nh\u00f3m",
+  "nh\u1ea1c",
+  "nh\u1eadt",
+  "nh\u1eafn",
+  "nh\u1edb",
+  "nit",
+  "n\u00e0y",
+  "n\u00e2ng",
+  "n\u0103m",
+  "n\u0103ng",
+  "n\u1ea5u",
+  "n\u1eb5ng",
+  "n\u1ed9i",
+  "n\u1ed9p",
+  "n\u1eefa",
+  "o",
+  "ode",
+  "oga",
+  "ong",
+  "online",
+  "o\u00e0i",
+  "o\u00e0n",
+  "o\u00e1n",
+  "o\u1ea1i",
+  "o\u1ea1n",
+  "o\u1ea1t",
+  "p",
+  "pha",
+  "phim",
+  "phi\u00ean",
+  "ph\u00e1p",
+  "ph\u00ea",
+  "ph\u00f2ng",
+  "ph\u00fac",
+  "ph\u00fat",
+  "ph\u01b0\u01a1ng",
+  "ph\u1ea3i",
+  "ph\u1ea9m",
+  "ph\u1ecfng",
+  "product",
+  "q",
+  "qa",
+  "qu\u00e2n",
+  "qu\u00fd",
+  "qu\u1ed1c",
+  "r",
+  "rau",
+  "release",
+  "review",
+  "r\u00e2m",
+  "r\u0103ng",
+  "r\u01b0a",
+  "r\u1ed5",
+  "r\u1eeda",
+  "s",
+  "sau",
+  "server",
+  "sinh",
+  "si\u00eau",
+  "slide",
+  "so\u1ea1n",
+  "sprint",
+  "stream",
+  "s\u00e0i",
+  "s\u00e1ch",
+  "s\u00e1ng",
+  "s\u00e1u",
+  "s\u01a1",
+  "s\u1eafp",
+  "s\u1ebd",
+  "s\u1ebfp",
+  "s\u1ee9c",
+  "s\u1eed",
+  "s\u1eeda",
+  "t",
+  "tar",
+  "task",
+  "team",
+  "test",
+  "tham",
+  "thi",
+  "tho\u1ea1i",
+  "thuy\u1ebft",
+  "th\u00e0nh",
+  "th\u00e1ng",
+  "th\u00eam",
+  "th\u00ed",
+  "th\u01b0",
+  "th\u1ea3o",
+  "th\u1ea7u",
+  "th\u1eafng",
+  "th\u1ec3",
+  "th\u1ecb",
+  "th\u1ed1ng",
+  "th\u1ee9",
+  "th\u1ee9 2",
+  "th\u1ee9 3",
+  "th\u1ee9 4",
+  "th\u1ee9 5",
+  "th\u1ee9 6",
+  "th\u1ee9 7",
+  "th\u1ee9 Ba",
+  "th\u1ee9 B\u1ea3y",
+  "th\u1ee9 Hai",
+  "th\u1ee9 N\u0103m",
+  "th\u1ee9 S\u00e1u",
+  "th\u1ee9 T\u01b0",
+  "th\u1ee9 ba",
+  "th\u1ee9 b\u1ea3y",
+  "th\u1ee9 hai",
+  "th\u1ee9 n\u0103m",
+  "th\u1ee9 s\u00e1u",
+  "th\u1ee9 t\u01b0",
+  "th\u1ef1c",
+  "tin",
+  "ti\u1ebfng",
+  "ti\u1ec1n",
+  "ti\u1ec3u",
+  "ti\u1ec7c",
+  "to\u00e1n",
+  "tra",
+  "training",
+  "tri\u1ec3n",
+  "trong",
+  "trung",
+  "tr\u00e2m",
+  "tr\u00ecnh",
+  "tr\u01b0a",
+  "tr\u01b0\u1edbc",
+  "tu\u1ea5n",
+  "tu\u1ea7n",
+  "ty",
+  "t\u00e0i",
+  "t\u00e0u",
+  "t\u00e1c",
+  "t\u00e2m",
+  "t\u00f4i",
+  "t\u01b0",
+  "t\u1ea1i",
+  "t\u1eadp",
+  "t\u1ebf",
+  "t\u1ed1i",
+  "t\u1ed5",
+  "t\u1edbi",
+  "t\u1ee5",
+  "t\u1eeb",
+  "u",
+  "uct",
+  "ule",
+  "ung",
+  "unit",
+  "uth",
+  "u\u00e2n",
+  "u\u1ea5n",
+  "u\u1ea7n",
+  "u\u1ea9n",
+  "u\u1eadn",
+  "u\u1ed1c",
+  "u\u1ed1i",
+  "u\u1ed1n",
+  "u\u1ed1ng",
+  "u\u1ed5i",
+  "v",
+  "ver",
+  "vi",
+  "video",
+  "vi\u00ean",
+  "vi\u1ebft",
+  "vi\u1ec7c",
+  "vi\u1ec7n",
+  "vi\u1ec7t",
+  "v\u00e0",
+  "v\u00e0o",
+  "v\u0103n",
+  "v\u0169ng",
+  "v\u1ea5n",
+  "v\u1eadt",
+  "v\u1ec1",
+  "v\u1edbi",
+  "w",
+  "workshop",
+  "x",
+  "xe",
+  "xem",
+  "xin",
+  "xx",
+  "xxx",
+  "xxx Xx",
+  "xxx Xxx",
+  "xxx d",
+  "xxx xxx",
+  "xxx xxxx",
+  "xxxx",
+  "x\u1ebfp",
+  "y",
+  "yoga",
+  "y\u1ebft",
+  "y\u1ec1n",
+  "y\u1ec7n",
+  "z",
+  "\u00a0",
+  "\u00d4",
+  "\u00d4n",
+  "\u00e0ng",
+  "\u00e0nh",
+  "\u00e1",
+  "\u00e1ch",
+  "\u00e1n",
+  "\u00e1ng",
+  "\u00e2ng",
+  "\u00ecnh",
+  "\u00ednh",
+  "\u00f2ng",
+  "\u00f3ng",
+  "\u00f4",
+  "\u00f4n",
+  "\u00f4ng",
+  "\u00f9ng",
+  "\u00fang",
+  "\u0103",
+  "\u0103n",
+  "\u0103ng",
+  "\u0110",
+  "\u0110i",
+  "\u0110\u00e0",
+  "\u0110\u1ecba",
+  "\u0110\u1ecdc",
+  "\u0110\u1ee9c",
+  "\u0111",
+  "\u0111a",
+  "\u0111i",
+  "\u0111i\u1ec7n",
+  "\u0111\u00e0",
+  "\u0111\u00e1",
+  "\u0111\u00ecnh",
+  "\u0111\u00f3n",
+  "\u0111\u00f3ng",
+  "\u0111\u01b0a",
+  "\u0111\u1ea7u",
+  "\u0111\u1eb7t",
+  "\u0111\u1ebfn",
+  "\u0111\u1ec1",
+  "\u0111\u1ecba",
+  "\u0111\u1ecdc",
+  "\u0111\u1ed1i",
+  "\u0111\u1ed3",
+  "\u0111\u1ed3ng",
+  "\u0111\u1ed9i",
+  "\u0111\u1ee9c",
+  "\u0169ng",
+  "\u01a1ng",
+  "\u01b0ng",
+  "\u01b0\u1edbc",
+  "\u01b0\u1edbi",
+  "\u1ea1ch",
+  "\u1ea1nh",
+  "\u1ea3ng",
+  "\u1eafng",
+  "\u1eb5ng",
+  "\u1ebfng",
+  "\u1ec7nh",
+  "\u1ecbch",
+  "\u1ecfng",
+  "\u1ed1ng",
+  "\u1ed3ng",
+  "\u1edbng",
+  "\u1eddng",
+  "\u1edf",
+  "\u1ee5ng",
+  "\u1ee9",
+  "\u1ee9 2",
+  "\u1ee9 3",
+  "\u1ee9 4",
+  "\u1ee9 5",
+  "\u1ee9 6",
+  "\u1ee9 7",
+  "\u1ee9ng"
+]

vocab/vectors.cfg

@@ -0,0 +1,3 @@
+{
+  "mode":"default"
+}