Update spaCy pipeline

.gitattributes

@@ -35,3 +35,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 en_pipeline-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
 transformer/model filter=lfs diff=lfs merge=lfs -text
+tok2vec/model filter=lfs diff=lfs merge=lfs -text
+vocab/key2row filter=lfs diff=lfs merge=lfs -text
+vocab/strings.json filter=lfs diff=lfs merge=lfs -text
+vocab/vectors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -13,22 +13,22 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.990135635
+      value: 0.9809885932
     - name: NER Recall
       type: recall
-      value: 0.9938118812
+      value: 0.9662921348
     - name: NER F Score
       type: f_score
-      value: 0.9919703521
+      value: 0.9735849057
 ---
 | Feature | Description |
 | --- | --- |
 | **Name** | `en_pipeline` |
 | **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) |
+| **Default Pipeline** | `tok2vec`, `ner` |
+| **Components** | `tok2vec`, `ner` |
+| **Vectors** | 514157 keys, 514157 unique vectors (300 dimensions) |
 | **Sources** | n/a |
 | **License** | n/a |
 | **Author** | [n/a]() |
@@ -49,8 +49,8 @@ model-index:
 
 | Type | Score |
 | --- | --- |
-| `ENTS_F` | 99.20 |
-| `ENTS_P` | 99.01 |
-| `ENTS_R` | 99.38 |
-| `TRANSFORMER_LOSS` | 37155.37 |
-| `NER_LOSS` | 36322.72 |
+| `ENTS_F` | 97.36 |
+| `ENTS_P` | 98.10 |
+| `ENTS_R` | 96.63 |
+| `TOK2VEC_LOSS` | 4351.47 |
+| `NER_LOSS` | 53052.01 |

config.cfg

@@ -1,147 +1,145 @@
-[paths]
-train = "/content/drive/MyDrive/sit/train3.spacy"
-dev = "/content/drive/MyDrive/sit/train3.spacy"
-vectors = null
-init_tok2vec = null
-
-[system]
-gpu_allocator = "pytorch"
-seed = 0
-
-[nlp]
-lang = "en"
-pipeline = ["transformer","ner"]
-batch_size = 128
-disabled = []
-before_creation = null
-after_creation = null
-after_pipeline_creation = null
-tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
-vectors = {"@vectors":"spacy.Vectors.v1"}
-
-[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 = false
-nO = null
-
-[components.ner.model.tok2vec]
-@architectures = "spacy-transformers.TransformerListener.v1"
-grad_factor = 1.0
-pooling = {"@layers":"reduce_mean.v1"}
-upstream = "*"
-
-[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 = "roberta-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}
-max_length = 0
-gold_preproc = false
-limit = 0
-augmenter = null
-
-[corpora.train]
-@readers = "spacy.Corpus.v1"
-path = ${paths.train}
-max_length = 0
-gold_preproc = false
-limit = 0
-augmenter = null
-
-[training]
-accumulate_gradient = 3
-dev_corpus = "corpora.dev"
-train_corpus = "corpora.train"
-seed = ${system.seed}
-gpu_allocator = ${system.gpu_allocator}
-dropout = 0.1
-patience = 1600
-max_epochs = 0
-max_steps = 20000
-eval_frequency = 200
-frozen_components = []
-annotating_components = []
-before_to_disk = null
-before_update = null
-
-[training.batcher]
-@batchers = "spacy.batch_by_padded.v1"
-discard_oversize = true
-size = 2000
-buffer = 256
-get_length = null
-
-[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
-
-[training.optimizer.learn_rate]
-@schedules = "warmup_linear.v1"
-warmup_steps = 250
-total_steps = 20000
-initial_rate = 0.00005
-
-[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]
-
+[paths]
+train = "sit/train3.spacy"
+dev = "sit/train3.spacy"
+vectors = "en_core_web_lg"
+init_tok2vec = null
+
+[system]
+gpu_allocator = null
+seed = 0
+
+[nlp]
+lang = "en"
+pipeline = ["tok2vec","ner"]
+batch_size = 1000
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+vectors = {"@vectors":"spacy.Vectors.v1"}
+
+[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.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+upstream = "*"
+
+[components.tok2vec]
+factory = "tok2vec"
+
+[components.tok2vec.model]
+@architectures = "spacy.Tok2Vec.v2"
+
+[components.tok2vec.model.embed]
+@architectures = "spacy.MultiHashEmbed.v2"
+width = ${components.tok2vec.model.encode.width}
+attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
+rows = [5000,1000,2500,2500]
+include_static_vectors = true
+
+[components.tok2vec.model.encode]
+@architectures = "spacy.MaxoutWindowEncoder.v2"
+width = 256
+depth = 8
+window_size = 1
+maxout_pieces = 3
+
+[corpora]
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[training]
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+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 = []
+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]

en_pipeline-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b04198a3f2c06fe095a8998d16f09de0e1a473b7af51c863e6e7ce98a8c4d103
-size 425480884
+oid sha256:80101df649014209b9cc7184f4d506c644567157f4fe7f60d4e5cb3d63435d63
+size 606693843

meta.json

@@ -10,13 +10,13 @@
   "spacy_version":">=3.7.5,<3.8.0",
   "spacy_git_version":"a6d0fc360",
   "vectors":{
-    "width":0,
-    "vectors":0,
-    "keys":0,
-    "name":null
+    "width":300,
+    "vectors":514157,
+    "keys":514157,
+    "name":"en_vectors"
   },
   "labels":{
-    "transformer":[
+    "tok2vec":[
 
     ],
     "ner":[
@@ -33,35 +33,35 @@
     ]
   },
   "pipeline":[
-    "transformer",
+    "tok2vec",
     "ner"
   ],
   "components":[
-    "transformer",
+    "tok2vec",
     "ner"
   ],
   "disabled":[
 
   ],
   "performance":{
-    "ents_f":0.9919703521,
-    "ents_p":0.990135635,
-    "ents_r":0.9938118812,
+    "ents_f":0.9735849057,
+    "ents_p":0.9809885932,
+    "ents_r":0.9662921348,
     "ents_per_type":{
       "SI UNIT ":{
-        "p":0.9880239521,
-        "r":0.99,
-        "f":0.989010989
+        "p":0.9794238683,
+        "r":0.9596774194,
+        "f":0.9694501018
       },
       "TIME UNIT":{
-        "p":1.0,
+        "p":0.9957081545,
         "r":1.0,
-        "f":1.0
+        "f":0.9978494624
       },
       "NUMBER":{
-        "p":1.0,
+        "p":0.6666666667,
         "r":1.0,
-        "f":1.0
+        "f":0.8
       },
       "THOUSANDS OPERATOR":{
         "p":1.0,
@@ -70,8 +70,8 @@
       },
       "OPERATOR":{
         "p":1.0,
-        "r":1.0,
-        "f":1.0
+        "r":0.3333333333,
+        "f":0.5
       },
       "FRACTION":{
         "p":1.0,
@@ -79,9 +79,9 @@
         "f":1.0
       },
       "CHEMICAL TERM":{
-        "p":0.9814814815,
-        "r":1.0,
-        "f":0.9906542056
+        "p":0.98,
+        "r":0.9245283019,
+        "f":0.9514563107
       },
       "DECIMAL":{
         "p":0.6666666667,
@@ -94,15 +94,15 @@
         "f":1.0
       },
       "RATIO":{
-        "p":1.0,
-        "r":1.0,
-        "f":1.0
+        "p":0.75,
+        "r":0.75,
+        "f":0.75
       }
     },
-    "transformer_loss":371.5536569223,
-    "ner_loss":363.2272483482
+    "tok2vec_loss":43.5147486759,
+    "ner_loss":530.5200964366
   },
   "requirements":[
-    "spacy-transformers>=1.3.5,<1.4.0"
+
   ]
 }

ner/cfg

@@ -1,13 +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
+{
+  "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

@@ -1 +1 @@
-��moves��{"0":{},"1":{"SI UNIT ":1069,"TIME UNIT":447,"CHEMICAL TERM":72,"LEADING ZERO":6,"RATIO":5,"OPERATOR":5,"NUMBER":3,"FRACTION":3,"DECIMAL":2,"THOUSANDS OPERATOR":1},"2":{"SI UNIT ":1069,"TIME UNIT":447,"CHEMICAL TERM":72,"LEADING ZERO":6,"RATIO":5,"OPERATOR":5,"NUMBER":3,"FRACTION":3,"DECIMAL":2,"THOUSANDS OPERATOR":1},"3":{"SI UNIT ":1069,"TIME UNIT":447,"CHEMICAL TERM":72,"LEADING ZERO":6,"RATIO":5,"OPERATOR":5,"NUMBER":3,"FRACTION":3,"DECIMAL":2,"THOUSANDS OPERATOR":1},"4":{"SI UNIT ":1069,"TIME UNIT":447,"CHEMICAL TERM":72,"LEADING ZERO":6,"RATIO":5,"OPERATOR":5,"NUMBER":3,"FRACTION":3,"DECIMAL":2,"THOUSANDS OPERATOR":1,"":1},"5":{"":1}}�cfg��neg_key�
+��moves��{"0":{},"1":{"SI UNIT ":950,"TIME UNIT":447,"CHEMICAL TERM":72,"LEADING ZERO":6,"RATIO":5,"OPERATOR":3,"FRACTION":3,"NUMBER":2,"DECIMAL":2,"THOUSANDS OPERATOR":1},"2":{"SI UNIT ":950,"TIME UNIT":447,"CHEMICAL TERM":72,"LEADING ZERO":6,"RATIO":5,"OPERATOR":3,"FRACTION":3,"NUMBER":2,"DECIMAL":2,"THOUSANDS OPERATOR":1},"3":{"SI UNIT ":950,"TIME UNIT":447,"CHEMICAL TERM":72,"LEADING ZERO":6,"RATIO":5,"OPERATOR":3,"FRACTION":3,"NUMBER":2,"DECIMAL":2,"THOUSANDS OPERATOR":1},"4":{"SI UNIT ":950,"TIME UNIT":447,"CHEMICAL TERM":72,"LEADING ZERO":6,"RATIO":5,"OPERATOR":3,"FRACTION":3,"NUMBER":2,"DECIMAL":2,"THOUSANDS OPERATOR":1,"":1},"5":{"":1}}�cfg��neg_key�

tok2vec/cfg

@@ -0,0 +1,3 @@
+{
+
+}

tok2vec/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f436ab3fe63a7935643dc2890ec798a590ef1ed217ff377666230aed918e0412
+size 34434008

vocab/key2row

@@ -1 +1,3 @@
-�
+version https://git-lfs.github.com/spec/v1
+oid sha256:31566ae010da3d399eb1d930ae142757afd2601034a4be3bdb00d18881c8c06a
+size 7066303

vocab/strings.json

@@ -1,2416 +1,3 @@
-[
-  "\t",
-  "\n",
-  "\r",
-  " ",
-  "  ",
-  "\"",
-  "'",
-  "''",
-  "'-(",
-  "'-)",
-  "'Cause",
-  "'Cos",
-  "'Coz",
-  "'Cuz",
-  "'S",
-  "'X",
-  "'Xxx",
-  "'Xxxxx",
-  "'am",
-  "'bout",
-  "'cause",
-  "'cos",
-  "'coz",
-  "'cuz",
-  "'d",
-  "'em",
-  "'ll",
-  "'m",
-  "'nuff",
-  "'re",
-  "'s",
-  "'ve",
-  "'x",
-  "'xx",
-  "'xxx",
-  "'xxxx",
-  "'y",
-  "(",
-  "(((",
-  "(*>",
-  "(*_*)",
-  "(-8",
-  "(-:",
-  "(-;",
-  "(-_-)",
-  "(-d",
-  "(._.)",
-  "(:",
-  "(;",
-  "(=",
-  "(>_<)",
-  "(^_^)",
-  "(o:",
-  "(x:",
-  "(x_x)",
-  "(\u00ac_\u00ac)",
-  "(\u0ca0_\u0ca0)",
-  "(\u256f\u00b0\u25a1\u00b0\uff09\u256f\ufe35\u253b\u2501\u253b",
-  ")",
-  ")))",
-  ")-:",
-  ")/\u00af",
-  "):",
-  "*",
-  ",",
-  "-",
-  "-((",
-  "-))",
-  "-/",
-  "-0",
-  "-10",
-  "-128.6",
-  "-15",
-  "-17.78",
-  "-18",
-  "-20",
-  "-3",
-  "-30",
-  "-40",
-  "-459.67",
-  "-5",
-  "-8",
-  "-80",
-  "-89.2",
-  "-D",
-  "-O",
-  "-P",
-  "-X",
-  "-_-",
-  "-__-",
-  "-d",
-  "-dd",
-  "-dd.d",
-  "-dd.dd",
-  "-ddd.d",
-  "-ddd.dd",
-  "-o",
-  "-p",
-  "-x",
-  "-|",
-  ".",
-  ".05",
-  ".15",
-  ".25",
-  ".44",
-  ".58",
-  ".67",
-  ".75",
-  ".77",
-  ".78",
-  ".C.",
-  ".D.",
-  ".E.",
-  ".G.",
-  ".H.",
-  ".J.",
-  ".M.",
-  ".Y.",
-  "._.",
-  ".e.",
-  ".g.",
-  ".m.",
-  ".s.",
-  "/",
-  "/3",
-  "/d",
-  "/or",
-  "0",
-  "0.0",
-  "0.05",
-  "0.1",
-  "0.2",
-  "0.25",
-  "0.3",
-  "0.4",
-  "0.5",
-  "0.6",
-  "0.75",
-  "0.o",
-  "000",
-  "022",
-  "0_0",
-  "0_o",
-  "0\u00b2\u00b3",
-  "1",
-  "1,000",
-  "1.2",
-  "1.5",
-  "1.8",
-  "10",
-  "10,000",
-  "100",
-  "100,000",
-  "1000",
-  "105",
-  "10a.m",
-  "10a.m.",
-  "10p.m",
-  "10p.m.",
-  "10\u00b2\u00b3",
-  "11",
-  "110",
-  "1100",
-  "11a.m",
-  "11a.m.",
-  "11p.m",
-  "11p.m.",
-  "12",
-  "120",
-  "120,000",
-  "1200",
-  "12a.m",
-  "12a.m.",
-  "12p.m",
-  "12p.m.",
-  "134",
-  "140,000",
-  "1400",
-  "15",
-  "15,000",
-  "150",
-  "150,000",
-  "1500",
-  "16",
-  "160,000",
-  "18",
-  "180",
-  "1800",
-  "195",
-  "1:2",
-  "1:3",
-  "1a.m",
-  "1a.m.",
-  "1p.m",
-  "1p.m.",
-  "2",
-  "2.2",
-  "2.4",
-  "2.5",
-  "20",
-  "20,000",
-  "200",
-  "200,000",
-  "2000",
-  "212",
-  "22",
-  "22.4",
-  "220,000",
-  "23",
-  "23.77",
-  "2300",
-  "25",
-  "25,000",
-  "250",
-  "2500",
-  "26",
-  "27",
-  "2700",
-  "273.15",
-  "28",
-  "2:1",
-  "2a.m",
-  "2a.m.",
-  "2p.m",
-  "2p.m.",
-  "3",
-  "3,000",
-  "3.2",
-  "3.5",
-  "30",
-  "30,000",
-  "300",
-  "3000",
-  "32",
-  "33",
-  "333",
-  "35",
-  "350",
-  "3500",
-  "37",
-  "37.78",
-  "373.15",
-  "3:1",
-  "3a.m",
-  "3a.m.",
-  "3p.m",
-  "3p.m.",
-  "4",
-  "40",
-  "400",
-  "4000",
-  "42.195",
-  "44",
-  "45",
-  "450",
-  "4500",
-  "4a.m",
-  "4a.m.",
-  "4p.m",
-  "4p.m.",
-  "5",
-  "5.3",
-  "5/9",
-  "50",
-  "500",
-  "5000",
-  "58.44",
-  "5a.m",
-  "5a.m.",
-  "5p.m",
-  "5p.m.",
-  "6",
-  "6.022",
-  "60",
-  "600",
-  "6000",
-  "6a.m",
-  "6a.m.",
-  "6p.m",
-  "6p.m.",
-  "7",
-  "700",
-  "7000",
-  "71",
-  "72",
-  "75",
-  "75.3",
-  "7a.m",
-  "7a.m.",
-  "7p.m",
-  "7p.m.",
-  "8",
-  "8)",
-  "8-",
-  "8-)",
-  "8-D",
-  "8-d",
-  "8.6",
-  "80",
-  "80,000",
-  "800",
-  "8000",
-  "85",
-  "8D",
-  "8a.m",
-  "8a.m.",
-  "8d",
-  "8p.m",
-  "8p.m.",
-  "9",
-  "9.2",
-  "9.58",
-  "90",
-  "900",
-  "9000",
-  "95",
-  "98.6",
-  "9a.m",
-  "9a.m.",
-  "9p.m",
-  "9p.m.",
-  ":",
-  ":'(",
-  ":')",
-  ":'-(",
-  ":'-)",
-  ":(",
-  ":((",
-  ":(((",
-  ":()",
-  ":)",
-  ":))",
-  ":)))",
-  ":*",
-  ":-(",
-  ":-((",
-  ":-(((",
-  ":-)",
-  ":-))",
-  ":-)))",
-  ":-*",
-  ":-/",
-  ":-0",
-  ":-3",
-  ":->",
-  ":-D",
-  ":-O",
-  ":-P",
-  ":-X",
-  ":-]",
-  ":-d",
-  ":-o",
-  ":-p",
-  ":-x",
-  ":-|",
-  ":-}",
-  ":/",
-  ":0",
-  ":1",
-  ":3",
-  ":>",
-  ":D",
-  ":O",
-  ":P",
-  ":X",
-  ":]",
-  ":d",
-  ":o",
-  ":o)",
-  ":p",
-  ":x",
-  ":x)",
-  ":|",
-  ":}",
-  ":\u2019(",
-  ":\u2019)",
-  ":\u2019-(",
-  ":\u2019-)",
-  ";",
-  ";)",
-  ";-)",
-  ";-D",
-  ";-X",
-  ";-d",
-  ";D",
-  ";X",
-  ";_;",
-  ";d",
-  "<",
-  "<.<",
-  "</3",
-  "</d",
-  "<3",
-  "<33",
-  "<333",
-  "<d",
-  "<dd",
-  "<ddd",
-  "<space>",
-  "<xxxx>",
-  "=",
-  "=(",
-  "=)",
-  "=/",
-  "=3",
-  "=D",
-  "=X",
-  "=[",
-  "=]",
-  "=d",
-  "=|",
-  ">",
-  ">.<",
-  ">.>",
-  ">:(",
-  ">:o",
-  ">:x",
-  "><(((*>",
-  "?",
-  "@",
-  "@_@",
-  "A",
-  "About",
-  "Absolute",
-  "Adm",
-  "Adm.",
-  "Ai",
-  "Ak",
-  "Ak.",
-  "Ala",
-  "Ala.",
-  "Alabama",
-  "Alaska",
-  "Antarctica",
-  "Apr",
-  "Apr.",
-  "April",
-  "Arctic",
-  "Are",
-  "Ariz",
-  "Ariz.",
-  "Arizona",
-  "Ark",
-  "Ark.",
-  "Arkansas",
-  "At",
-  "Aug",
-  "Aug.",
-  "August",
-  "Autumn",
-  "Avogadro",
-  "B",
-  "BER",
-  "Bros",
-  "Bros.",
-  "C",
-  "C'm",
-  "C++",
-  "C.",
-  "CHEMICAL TERM",
-  "Ca",
-  "Calif",
-  "Calif.",
-  "California",
-  "Can",
-  "Cause",
-  "Cd",
-  "Celsius",
-  "Co",
-  "Co.",
-  "Colo",
-  "Colo.",
-  "Colorado",
-  "Conn",
-  "Conn.",
-  "Connecticut",
-  "Corp",
-  "Corp.",
-  "Cos",
-  "Could",
-  "Coz",
-  "Cuz",
-  "C\u2019m",
-  "D",
-  "D.",
-  "D.C.",
-  "DECIMAL",
-  "Dare",
-  "Death",
-  "Dec",
-  "Dec.",
-  "December",
-  "Del",
-  "Del.",
-  "Delaware",
-  "Did",
-  "Do",
-  "Does",
-  "Doin",
-  "Doin'",
-  "Doin\u2019",
-  "Dr",
-  "Dr.",
-  "During",
-  "E",
-  "E.G.",
-  "E.g",
-  "E.g.",
-  "ERM",
-  "ERO",
-  "Each",
-  "F",
-  "F.",
-  "FRACTION",
-  "Fahrenheit",
-  "Feb",
-  "Feb.",
-  "February",
-  "Fla",
-  "Fla.",
-  "Florida",
-  "G",
-  "Ga",
-  "Ga.",
-  "Gen",
-  "Gen.",
-  "Georgia",
-  "Goin",
-  "Goin'",
-  "Goin\u2019",
-  "Gon",
-  "Got",
-  "Gov",
-  "Gov.",
-  "H",
-  "Had",
-  "Has",
-  "Have",
-  "Havin",
-  "Havin'",
-  "Havin\u2019",
-  "He",
-  "He's",
-  "Heatstroke",
-  "He\u2019s",
-  "His",
-  "How",
-  "How's",
-  "How\u2019s",
-  "I",
-  "I.E.",
-  "I.e",
-  "I.e.",
-  "ION",
-  "IT ",
-  "Ia",
-  "Ia.",
-  "Ice",
-  "Id",
-  "Id.",
-  "Idaho",
-  "Ill",
-  "Ill.",
-  "Illinois",
-  "In",
-  "Inc",
-  "Inc.",
-  "Ind",
-  "Ind.",
-  "Indiana",
-  "Iowa",
-  "Is",
-  "It",
-  "It's",
-  "It\u2019s",
-  "J",
-  "Jan",
-  "Jan.",
-  "January",
-  "Jr",
-  "Jr.",
-  "Jul",
-  "Jul.",
-  "July",
-  "Jun",
-  "Jun.",
-  "June",
-  "K",
-  "K.",
-  "Kan",
-  "Kan.",
-  "Kans",
-  "Kans.",
-  "Kansas",
-  "Kelvin",
-  "Kentucky",
-  "Ky",
-  "Ky.",
-  "L",
-  "LEADING ZERO",
-  "LED",
-  "La",
-  "La.",
-  "Let",
-  "Let's",
-  "Let\u2019s",
-  "Louisiana",
-  "Lovin",
-  "Lovin'",
-  "Lovin\u2019",
-  "Ltd",
-  "Ltd.",
-  "Luminous",
-  "M",
-  "MAL",
-  "Ma'am",
-  "Mar",
-  "Mar.",
-  "March",
-  "Mars",
-  "Mass",
-  "Mass.",
-  "Massachusetts",
-  "May",
-  "Ma\u2019am",
-  "Md",
-  "Md.",
-  "Mediterranean",
-  "Messrs",
-  "Messrs.",
-  "Mich",
-  "Mich.",
-  "Michigan",
-  "Might",
-  "Minn",
-  "Minn.",
-  "Minnesota",
-  "Miss",
-  "Miss.",
-  "Mississippi",
-  "Mo",
-  "Mo.",
-  "Molar",
-  "Mole",
-  "Mont",
-  "Mont.",
-  "Mount",
-  "Mr",
-  "Mr.",
-  "Mrs",
-  "Mrs.",
-  "Ms",
-  "Ms.",
-  "Mt",
-  "Mt.",
-  "Must",
-  "N",
-  "N.C.",
-  "N.D.",
-  "N.H.",
-  "N.J.",
-  "N.M.",
-  "N.Y.",
-  "NIT",
-  "NUMBER",
-  "Neb",
-  "Neb.",
-  "Nebr",
-  "Nebr.",
-  "Nebraska",
-  "Need",
-  "Nev",
-  "Nev.",
-  "Nevada",
-  "New Hampshire",
-  "New Jersey",
-  "New Mexico",
-  "New York",
-  "North Carolina",
-  "North Dakota",
-  "Not",
-  "Nothin",
-  "Nothin'",
-  "Nothin\u2019",
-  "Nov",
-  "Nov.",
-  "November",
-  "Nuthin",
-  "Nuthin'",
-  "Nuthin\u2019",
-  "O",
-  "O'clock",
-  "O.O",
-  "O.o",
-  "OPERATOR",
-  "O_O",
-  "O_o",
-  "Oct",
-  "Oct.",
-  "October",
-  "Okla",
-  "Okla.",
-  "Oklahoma",
-  "Ol",
-  "Ol'",
-  "Ol\u2019",
-  "One",
-  "Ore",
-  "Ore.",
-  "Oregon",
-  "Ought",
-  "O\u2019clock",
-  "P",
-  "Pa",
-  "Pa.",
-  "Pennsylvania",
-  "Ph",
-  "Ph.D.",
-  "Please",
-  "Prof",
-  "Prof.",
-  "R",
-  "RATIO",
-  "ROOT",
-  "Rep",
-  "Rep.",
-  "Rev",
-  "Rev.",
-  "Room",
-  "S",
-  "S.C.",
-  "SI",
-  "SI UNIT ",
-  "STP",
-  "Sen",
-  "Sen.",
-  "Sep",
-  "Sep.",
-  "Sept",
-  "Sept.",
-  "September",
-  "Sha",
-  "She",
-  "She's",
-  "She\u2019s",
-  "Should",
-  "Snow",
-  "Somethin",
-  "Somethin'",
-  "Somethin\u2019",
-  "South Carolina",
-  "St",
-  "St.",
-  "Summer",
-  "T",
-  "THOUSANDS OPERATOR",
-  "TIME UNIT",
-  "TIO",
-  "TOR",
-  "Tenn",
-  "Tenn.",
-  "Tennessee",
-  "That",
-  "That's",
-  "That\u2019s",
-  "The",
-  "There",
-  "There's",
-  "There\u2019s",
-  "These",
-  "They",
-  "This",
-  "This's",
-  "This\u2019s",
-  "Those",
-  "Today",
-  "V",
-  "V.V",
-  "V_V",
-  "Va",
-  "Va.",
-  "Valley",
-  "Virginia",
-  "W",
-  "Was",
-  "Wash",
-  "Wash.",
-  "Washington",
-  "Water",
-  "We",
-  "Were",
-  "What",
-  "What's",
-  "What\u2019s",
-  "When",
-  "When's",
-  "When\u2019s",
-  "Where",
-  "Where's",
-  "Where\u2019s",
-  "Who",
-  "Who's",
-  "Who\u2019s",
-  "Why",
-  "Why's",
-  "Why\u2019s",
-  "Winter",
-  "Wis",
-  "Wis.",
-  "Wisconsin",
-  "Wo",
-  "Would",
-  "X'x",
-  "X'xxxx",
-  "X++",
-  "X.",
-  "X.X",
-  "X.X.",
-  "X.x",
-  "X.x.",
-  "XD",
-  "XDD",
-  "XX",
-  "XX XXXX ",
-  "XXX",
-  "XXXX",
-  "XXXX XXXX",
-  "X_X",
-  "X_x",
-  "Xx",
-  "Xx'",
-  "Xx'x",
-  "Xx'xx",
-  "Xx.",
-  "Xx.X.",
-  "Xxx",
-  "Xxx'x",
-  "Xxx.",
-  "Xxxx",
-  "Xxxx'",
-  "Xxxx'x",
-  "Xxxx.",
-  "Xxxxx",
-  "Xxxxx'",
-  "Xxxxx'x",
-  "Xxxxx.",
-  "Xxxxx\u2019",
-  "Xxxxx\u2019x",
-  "Xxxx\u2019",
-  "Xxxx\u2019x",
-  "Xxx\u2019x",
-  "Xx\u2019",
-  "Xx\u2019x",
-  "Xx\u2019xx",
-  "X\u2019x",
-  "X\u2019xxxx",
-  "Y",
-  "You",
-  "[",
-  "[-:",
-  "[:",
-  "[=",
-  "\\",
-  "\\\")",
-  "\\n",
-  "\\t",
-  "\\x",
-  "]",
-  "]=",
-  "^",
-  "^_^",
-  "^__^",
-  "^___^",
-  "_*)",
-  "_-)",
-  "_.)",
-  "_<)",
-  "_^)",
-  "__-",
-  "__^",
-  "_\u00ac)",
-  "_\u0ca0)",
-  "a",
-  "a.",
-  "a.m",
-  "a.m.",
-  "about",
-  "above",
-  "absolute",
-  "aby",
-  "ace",
-  "ach",
-  "acid",
-  "ack",
-  "activities",
-  "added",
-  "ade",
-  "adjustable",
-  "adm",
-  "adm.",
-  "ads",
-  "adult",
-  "advance",
-  "aft",
-  "after",
-  "age",
-  "ags",
-  "ai",
-  "ail",
-  "aim",
-  "ain",
-  "air",
-  "ait",
-  "ak",
-  "ak.",
-  "ake",
-  "ala",
-  "ala.",
-  "alarm",
-  "alk",
-  "all",
-  "allowance",
-  "als",
-  "also",
-  "am",
-  "ame",
-  "ammonia",
-  "amount",
-  "amp",
-  "ams",
-  "an",
-  "an.",
-  "and",
-  "and/or",
-  "ane",
-  "angle",
-  "ank",
-  "ans",
-  "ant",
-  "antarctica",
-  "antenna",
-  "any",
-  "ape",
-  "apples",
-  "approximately",
-  "apr",
-  "apr.",
-  "ar.",
-  "arctic",
-  "ard",
-  "are",
-  "arena",
-  "arf",
-  "ariz",
-  "ariz.",
-  "arizona",
-  "ark",
-  "ark.",
-  "arm",
-  "around",
-  "arrivals",
-  "arrive",
-  "arrived",
-  "arrives",
-  "arrow",
-  "ars",
-  "ary",
-  "as",
-  "ase",
-  "ash",
-  "ask",
-  "ass",
-  "ast",
-  "at",
-  "ate",
-  "ath",
-  "atmospheric",
-  "atoms",
-  "ats",
-  "aug",
-  "aug.",
-  "autumn",
-  "ave",
-  "average",
-  "averages",
-  "avogadro",
-  "ays",
-  "b",
-  "b.",
-  "baby",
-  "back",
-  "backpack",
-  "bag",
-  "baggage",
-  "bags",
-  "baked",
-  "baking",
-  "band",
-  "barbecue",
-  "barbell",
-  "base",
-  "based",
-  "basketball",
-  "be",
-  "beach",
-  "beacon",
-  "because",
-  "beep",
-  "beeped",
-  "began",
-  "begin",
-  "begins",
-  "bell",
-  "below",
-  "bench",
-  "ber",
-  "between",
-  "bicycle",
-  "billboard",
-  "birth",
-  "bit",
-  "ble",
-  "board",
-  "body",
-  "boiling",
-  "bon",
-  "books",
-  "bookshelf",
-  "bought",
-  "bout",
-  "box",
-  "br.",
-  "break",
-  "bridge",
-  "brightness",
-  "broke",
-  "bros",
-  "bros.",
-  "building",
-  "bus",
-  "buzzed",
-  "by",
-  "c",
-  "c'm",
-  "c++",
-  "c.",
-  "ca",
-  "cable",
-  "cal",
-  "calculated",
-  "calculations",
-  "calibrated",
-  "calif",
-  "calif.",
-  "call",
-  "calls",
-  "can",
-  "candle",
-  "capacity",
-  "car",
-  "carbon",
-  "carpet",
-  "carry",
-  "case",
-  "cat",
-  "cause",
-  "cd",
-  "ce>",
-  "cel",
-  "celsius",
-  "ces",
-  "ch.",
-  "changes",
-  "charge",
-  "checked",
-  "chemical",
-  "chemical term",
-  "chemist",
-  "chemistry",
-  "chloride",
-  "chlorine",
-  "cid",
-  "cil",
-  "class",
-  "classes",
-  "classroom",
-  "cle",
-  "climate",
-  "climax",
-  "clip",
-  "clocked",
-  "cm",
-  "cm\u00b2",
-  "co",
-  "co.",
-  "coastline",
-  "coffee",
-  "coldest",
-  "colo",
-  "colo.",
-  "come",
-  "comes",
-  "comfort",
-  "comfortable",
-  "commute",
-  "completed",
-  "compound",
-  "con",
-  "concentration",
-  "concept",
-  "concise",
-  "conclude",
-  "conditioner",
-  "conditions",
-  "conn",
-  "conn.",
-  "considered",
-  "constant",
-  "contain",
-  "contained",
-  "container",
-  "contains",
-  "convert",
-  "cookies",
-  "cooking",
-  "cooks",
-  "cooler",
-  "coolness",
-  "copper",
-  "cord",
-  "corp",
-  "corp.",
-  "corridor",
-  "cos",
-  "cost",
-  "could",
-  "countdown",
-  "court",
-  "coz",
-  "crane",
-  "cream",
-  "critical",
-  "crucial",
-  "ct.",
-  "cts",
-  "cue",
-  "cur",
-  "customer",
-  "cuz",
-  "cycle",
-  "c\u2019m",
-  "d",
-  "d)",
-  "d,ddd",
-  "d-",
-  "d-)",
-  "d-X",
-  "d.",
-  "d.c.",
-  "d.d",
-  "d.dd",
-  "d.ddd",
-  "d.x",
-  "d/d",
-  "d:d",
-  "dX",
-  "d_d",
-  "d_x",
-  "daily",
-  "dare",
-  "day",
-  "dd",
-  "dd,ddd",
-  "dd.d",
-  "dd.dd",
-  "dd.ddd",
-  "ddd",
-  "ddd,ddd",
-  "ddd.dd",
-  "dddd",
-  "ddx.x",
-  "ddx.x.",
-  "deadlift",
-  "death",
-  "dec",
-  "dec.",
-  "decimal",
-  "deck",
-  "ded",
-  "del",
-  "del.",
-  "delay",
-  "den",
-  "deo",
-  "depends",
-  "der",
-  "des",
-  "desert",
-  "design",
-  "determines",
-  "determining",
-  "device",
-  "dge",
-  "diagonal",
-  "did",
-  "dioxide",
-  "dip",
-  "direction",
-  "directly",
-  "display",
-  "displays",
-  "diving",
-  "dle",
-  "dly",
-  "dm.",
-  "do",
-  "dock",
-  "doctor",
-  "document",
-  "documentary",
-  "does",
-  "dog",
-  "doin",
-  "doin'",
-  "doing",
-  "doin\u2019",
-  "dor",
-  "dose",
-  "dow",
-  "dr",
-  "dr.",
-  "dress",
-  "drive",
-  "driveway",
-  "dro",
-  "drop",
-  "dropped",
-  "dumbbell",
-  "duration",
-  "during",
-  "dx.x",
-  "dx.x.",
-  "e",
-  "e's",
-  "e.",
-  "e.g",
-  "e.g.",
-  "each",
-  "ead",
-  "eak",
-  "eal",
-  "eam",
-  "ean",
-  "eat",
-  "eb.",
-  "ebr",
-  "ec.",
-  "ech",
-  "eck",
-  "ect",
-  "eds",
-  "eed",
-  "een",
-  "eep",
-  "eet",
-  "effectiveness",
-  "eit",
-  "el.",
-  "eld",
-  "elephant",
-  "elevator",
-  "elf",
-  "ell",
-  "els",
-  "elt",
-  "ely",
-  "em",
-  "emails",
-  "eme",
-  "emergency",
-  "emit",
-  "emits",
-  "emitted",
-  "empty",
-  "en",
-  "en.",
-  "ena",
-  "ended",
-  "ends",
-  "enjoys",
-  "enn",
-  "enough",
-  "ent",
-  "entities",
-  "ep.",
-  "eps",
-  "ept",
-  "equal",
-  "equals",
-  "equation",
-  "equipment",
-  "equivalent",
-  "ere",
-  "ero",
-  "ers",
-  "ert",
-  "ery",
-  "ese",
-  "ess",
-  "essential",
-  "est",
-  "ets",
-  "ev.",
-  "event",
-  "ever",
-  "every",
-  "exactly",
-  "exam",
-  "exceed",
-  "exceeded",
-  "exhibit",
-  "exit",
-  "experiment",
-  "extensively",
-  "extreme",
-  "e\u2019s",
-  "f",
-  "f.",
-  "fabric",
-  "fahrenheit",
-  "feb",
-  "feb.",
-  "fee",
-  "feels",
-  "fence",
-  "few",
-  "fic",
-  "field",
-  "film",
-  "finish",
-  "finished",
-  "fish",
-  "fishing",
-  "fla",
-  "fla.",
-  "flagpole",
-  "flame",
-  "flashlight",
-  "flight",
-  "floodlight",
-  "floodlights",
-  "flour",
-  "food",
-  "football",
-  "for",
-  "forecast",
-  "formula",
-  "fraction",
-  "freezer",
-  "freezes",
-  "freezing",
-  "frequency",
-  "from",
-  "fundamental",
-  "g",
-  "g.",
-  "ga",
-  "ga.",
-  "gage",
-  "gan",
-  "gar",
-  "garden",
-  "gas",
-  "gases",
-  "gasses",
-  "gauge",
-  "gen",
-  "gen.",
-  "ges",
-  "ghs",
-  "ght",
-  "gin",
-  "gle",
-  "glucose",
-  "gns",
-  "goes",
-  "goin",
-  "goin'",
-  "going",
-  "goin\u2019",
-  "gon",
-  "gonna",
-  "got",
-  "gov",
-  "gov.",
-  "grams",
-  "green",
-  "gth",
-  "h",
-  "h.",
-  "had",
-  "hall",
-  "hallway",
-  "han",
-  "has",
-  "hat",
-  "have",
-  "havin",
-  "havin'",
-  "having",
-  "havin\u2019",
-  "he",
-  "he's",
-  "headlamp",
-  "headlight",
-  "healthy",
-  "heat",
-  "heated",
-  "heats",
-  "heatstroke",
-  "heatwave",
-  "hed",
-  "helium",
-  "hen",
-  "her",
-  "hes",
-  "hey",
-  "he\u2019s",
-  "high",
-  "highest",
-  "hiking",
-  "hin",
-  "hip",
-  "his",
-  "hold",
-  "holds",
-  "hon",
-  "hose",
-  "hot",
-  "hour",
-  "hours",
-  "how",
-  "how's",
-  "how\u2019s",
-  "hr",
-  "hrs",
-  "hts",
-  "human",
-  "hydrogen",
-  "i",
-  "i.",
-  "i.e",
-  "i.e.",
-  "ia",
-  "ia.",
-  "ial",
-  "ica",
-  "ice",
-  "ich",
-  "ick",
-  "ics",
-  "id",
-  "id.",
-  "ide",
-  "ideal",
-  "ies",
-  "if.",
-  "ift",
-  "ify",
-  "igh",
-  "ign",
-  "ild",
-  "ill",
-  "ill.",
-  "ilm",
-  "ils",
-  "ily",
-  "ime",
-  "in",
-  "in'",
-  "inc",
-  "inc.",
-  "ind",
-  "ind.",
-  "indicates",
-  "indoors",
-  "ine",
-  "influences",
-  "ing",
-  "ink",
-  "inn",
-  "ins",
-  "int",
-  "intake",
-  "intensity",
-  "interval",
-  "in\u2019",
-  "ion",
-  "ipe",
-  "ire",
-  "is",
-  "is.",
-  "ise",
-  "ish",
-  "iss",
-  "ist",
-  "it",
-  "it's",
-  "ite",
-  "ith",
-  "its",
-  "ity",
-  "it\u2019s",
-  "ium",
-  "ius",
-  "ive",
-  "iz.",
-  "ize",
-  "j",
-  "j.",
-  "jan",
-  "jan.",
-  "jogging",
-  "jr",
-  "jr.",
-  "jul",
-  "jul.",
-  "july",
-  "jun",
-  "jun.",
-  "just",
-  "k",
-  "k.",
-  "kan",
-  "kan.",
-  "kans",
-  "kans.",
-  "ked",
-  "keeps",
-  "kelvin",
-  "kept",
-  "kg",
-  "kite",
-  "kla",
-  "km",
-  "ky",
-  "ky.",
-  "l",
-  "l.",
-  "la",
-  "la.",
-  "ladder",
-  "lamp",
-  "lamps",
-  "lane",
-  "lar",
-  "laser",
-  "last",
-  "lasted",
-  "lasting",
-  "law",
-  "lay",
-  "lds",
-  "leading zero",
-  "lecture",
-  "led",
-  "length",
-  "ler",
-  "les",
-  "less",
-  "let",
-  "let's",
-  "let\u2019s",
-  "ley",
-  "lid",
-  "lif",
-  "lift",
-  "lifted",
-  "light",
-  "lighting",
-  "lights",
-  "limit",
-  "line",
-  "lip",
-  "liquid",
-  "liter",
-  "liters",
-  "ll",
-  "ll.",
-  "lls",
-  "lly",
-  "lo.",
-  "load",
-  "long",
-  "loop",
-  "lose",
-  "loudly",
-  "lovin",
-  "lovin'",
-  "loving",
-  "lovin\u2019",
-  "low",
-  "lso",
-  "ltd",
-  "ltd.",
-  "lts",
-  "luggage",
-  "luminous",
-  "m",
-  "m.",
-  "mW",
-  "ma'am",
-  "mac",
-  "madam",
-  "mal",
-  "man",
-  "map",
-  "mar",
-  "mar.",
-  "marathon",
-  "mars",
-  "mass",
-  "mass.",
-  "max",
-  "maximum",
-  "may",
-  "ma\u2019am",
-  "md",
-  "md.",
-  "measure",
-  "measured",
-  "measures",
-  "measuring",
-  "meat",
-  "med",
-  "mediterranean",
-  "meeting",
-  "melt",
-  "melts",
-  "mer",
-  "mes",
-  "messrs",
-  "messrs.",
-  "met",
-  "meter",
-  "methane",
-  "mg",
-  "mich",
-  "mich.",
-  "microwave",
-  "might",
-  "mild",
-  "min",
-  "minn",
-  "minn.",
-  "minute",
-  "minutes",
-  "miss",
-  "miss.",
-  "mit",
-  "mo",
-  "mo.",
-  "molar",
-  "molarity",
-  "mole",
-  "molecules",
-  "moles",
-  "mol\u00b7K.",
-  "mol\u00b7k.",
-  "moment",
-  "mont",
-  "mont.",
-  "morning",
-  "movie",
-  "mps",
-  "mr",
-  "mr.",
-  "mrs",
-  "mrs.",
-  "ms",
-  "ms.",
-  "mt",
-  "mt.",
-  "mth",
-  "much",
-  "mum",
-  "must",
-  "mw",
-  "n",
-  "n's",
-  "n't",
-  "n.",
-  "n.c.",
-  "n.d.",
-  "n.h.",
-  "n.j.",
-  "n.m.",
-  "n.y.",
-  "na",
-  "nal",
-  "nc.",
-  "nce",
-  "nch",
-  "ncy",
-  "nd.",
-  "nds",
-  "neb",
-  "neb.",
-  "nebr",
-  "nebr.",
-  "necklace",
-  "ned",
-  "need",
-  "needs",
-  "nel",
-  "ner",
-  "nes",
-  "nev",
-  "nev.",
-  "new",
-  "nge",
-  "ngs",
-  "nia",
-  "nic",
-  "nighttime",
-  "nis",
-  "nit",
-  "nitrogen",
-  "nly",
-  "nn.",
-  "nna",
-  "noon",
-  "normal",
-  "not",
-  "nothin",
-  "nothin'",
-  "nothing",
-  "nothin\u2019",
-  "nov",
-  "nov.",
-  "now",
-  "ns.",
-  "nse",
-  "nt",
-  "nt.",
-  "nts",
-  "nuff",
-  "numbers",
-  "nuthin",
-  "nuthin'",
-  "nuthin\u2019",
-  "n\u2019s",
-  "n\u2019t",
-  "o",
-  "o'clock",
-  "o's",
-  "o.",
-  "o.0",
-  "o.O",
-  "o.o",
-  "o_0",
-  "o_O",
-  "o_o",
-  "oad",
-  "oar",
-  "occupies",
-  "occur",
-  "occurs",
-  "ock",
-  "oct",
-  "oct.",
-  "ody",
-  "oes",
-  "of",
-  "of.",
-  "off",
-  "office",
-  "often",
-  "oin",
-  "oke",
-  "okla",
-  "okla.",
-  "oks",
-  "ol",
-  "ol'",
-  "old",
-  "ole",
-  "olo",
-  "ol\u2019",
-  "oms",
-  "on",
-  "ona",
-  "ond",
-  "one",
-  "ong",
-  "only",
-  "onn",
-  "ons",
-  "ont",
-  "ood",
-  "ool",
-  "oom",
-  "oon",
-  "oop",
-  "oor",
-  "ope",
-  "operator",
-  "or",
-  "oranges",
-  "ord",
-  "ordered",
-  "ore",
-  "ore.",
-  "orp",
-  "ors",
-  "ort",
-  "ory",
-  "os.",
-  "ose",
-  "ost",
-  "ought",
-  "our",
-  "ous",
-  "out",
-  "outdoor",
-  "outside",
-  "ov.",
-  "ove",
-  "oven",
-  "overnight",
-  "overtime",
-  "own",
-  "ows",
-  "oxygen",
-  "oys",
-  "o\u2019clock",
-  "o\u2019s",
-  "p",
-  "p.",
-  "p.m",
-  "p.m.",
-  "pa",
-  "pa.",
-  "package",
-  "packets",
-  "pages",
-  "pan",
-  "panel",
-  "parade",
-  "parcel",
-  "park",
-  "particles",
-  "passengers",
-  "path",
-  "pay",
-  "payload",
-  "peak",
-  "ped",
-  "pencil",
-  "per",
-  "perfect",
-  "person",
-  "pet",
-  "ph",
-  "ph.d.",
-  "photometry",
-  "picnic",
-  "pipe",
-  "pitch",
-  "playground",
-  "plays",
-  "pleasant",
-  "please",
-  "plummet",
-  "plunge",
-  "pm",
-  "point",
-  "pointer",
-  "pole",
-  "pool",
-  "potassium",
-  "potatoes",
-  "power",
-  "pr.",
-  "predicts",
-  "prefers",
-  "preheated",
-  "prepared",
-  "presentation",
-  "press",
-  "pressure",
-  "prof",
-  "prof.",
-  "projector",
-  "proportional",
-  "pt.",
-  "pty",
-  "puzzle",
-  "q",
-  "q.",
-  "quantifies",
-  "quantify",
-  "r",
-  "r.",
-  "race",
-  "racing",
-  "raft",
-  "railway",
-  "ran",
-  "range",
-  "rarely",
-  "ratio",
-  "rce",
-  "rch",
-  "rds",
-  "re",
-  "re.",
-  "reach",
-  "reached",
-  "reaches",
-  "reaching",
-  "reaction",
-  "read",
-  "reads",
-  "recipe",
-  "recommended",
-  "record",
-  "recorded",
-  "red",
-  "refreshing",
-  "registered",
-  "relates",
-  "remaining",
-  "rep",
-  "rep.",
-  "represents",
-  "res",
-  "response",
-  "restaurant",
-  "rev",
-  "rev.",
-  "rge",
-  "ribbon",
-  "ric",
-  "rice",
-  "ride",
-  "rings",
-  "rip",
-  "river",
-  "riz",
-  "rk.",
-  "rns",
-  "rof",
-  "role",
-  "rom",
-  "room",
-  "rop",
-  "rope",
-  "ros",
-  "round",
-  "route",
-  "row",
-  "rp.",
-  "rry",
-  "rs.",
-  "rth",
-  "rts",
-  "rubber",
-  "ruler",
-  "running",
-  "runs",
-  "runtime",
-  "runway",
-  "s",
-  "s's",
-  "s.",
-  "s.c.",
-  "same",
-  "sauna",
-  "scarf",
-  "schedule",
-  "scheduled",
-  "scorching",
-  "screen",
-  "sec",
-  "second",
-  "seconds",
-  "sed",
-  "sell",
-  "sen",
-  "sen.",
-  "sep",
-  "sep.",
-  "sept",
-  "sept.",
-  "ser",
-  "served",
-  "service",
-  "serving",
-  "ses",
-  "session",
-  "set",
-  "sh.",
-  "sha",
-  "shade",
-  "shadow",
-  "shall",
-  "she",
-  "she's",
-  "shelf",
-  "she\u2019s",
-  "ship",
-  "shipment",
-  "shipping",
-  "should",
-  "showed",
-  "shows",
-  "si",
-  "si unit ",
-  "sign",
-  "signal",
-  "signboard",
-  "signs",
-  "size",
-  "sleeping",
-  "slide",
-  "slides",
-  "snow",
-  "soar",
-  "sodium",
-  "solid",
-  "solute",
-  "solution",
-  "somethin",
-  "somethin'",
-  "something",
-  "somethin\u2019",
-  "son",
-  "song",
-  "source",
-  "sources",
-  "space",
-  "span",
-  "spare",
-  "specific",
-  "speech",
-  "sports",
-  "spotlight",
-  "spring",
-  "sprint",
-  "sprinter",
-  "square",
-  "squat",
-  "srs",
-  "ss.",
-  "st",
-  "st.",
-  "stadium",
-  "staircase",
-  "standard",
-  "stands",
-  "started",
-  "starts",
-  "states",
-  "stick",
-  "stoichiometry",
-  "stopwatch",
-  "story",
-  "stp",
-  "street",
-  "streetlights",
-  "string",
-  "strip",
-  "study",
-  "submarine",
-  "substance",
-  "sufficient",
-  "sugar",
-  "suitable",
-  "sulfate",
-  "sulfuric",
-  "summer",
-  "support",
-  "swimming",
-  "synthesized",
-  "s\u2019s",
-  "t",
-  "t's",
-  "t.",
-  "ta",
-  "table",
-  "tail",
-  "take",
-  "tal",
-  "talk",
-  "tank",
-  "tape",
-  "tarmac",
-  "task",
-  "tch",
-  "td.",
-  "technical",
-  "ted",
-  "temperature",
-  "temperatures",
-  "ten",
-  "tenn",
-  "tenn.",
-  "tennis",
-  "tent",
-  "ter",
-  "tes",
-  "test",
-  "than",
-  "that",
-  "that's",
-  "that\u2019s",
-  "the",
-  "theater",
-  "them",
-  "there",
-  "there's",
-  "there\u2019s",
-  "thermometer",
-  "these",
-  "they",
-  "think",
-  "this",
-  "this's",
-  "this\u2019s",
-  "those",
-  "thousands operator",
-  "throughout",
-  "thy",
-  "tic",
-  "tie",
-  "time",
-  "time unit",
-  "timed",
-  "timer",
-  "tio",
-  "tly",
-  "to",
-  "today",
-  "tomorrow",
-  "tor",
-  "torch",
-  "total",
-  "tow",
-  "towel",
-  "towing",
-  "track",
-  "traffic",
-  "trail",
-  "train",
-  "transitions",
-  "trip",
-  "tropics",
-  "truck",
-  "try",
-  "tunnel",
-  "turned",
-  "turns",
-  "typically",
-  "t\u2019s",
-  "u",
-  "u.",
-  "ual",
-  "uat",
-  "uch",
-  "uck",
-  "ude",
-  "udy",
-  "uff",
-  "ug.",
-  "uge",
-  "uid",
-  "ul.",
-  "ula",
-  "uld",
-  "ule",
-  "ult",
-  "uly",
-  "ume",
-  "umn",
-  "un.",
-  "una",
-  "und",
-  "under",
-  "unit",
-  "uns",
-  "unt",
-  "up",
-  "ure",
-  "urs",
-  "urt",
-  "us",
-  "use",
-  "used",
-  "ust",
-  "ute",
-  "v",
-  "v.",
-  "v.s",
-  "v.s.",
-  "v.v",
-  "v_v",
-  "va",
-  "va.",
-  "vacations",
-  "val",
-  "valley",
-  "ve",
-  "ved",
-  "ven",
-  "ver",
-  "ves",
-  "video",
-  "vie",
-  "vin",
-  "visibility",
-  "volume",
-  "volumes",
-  "vs",
-  "vs.",
-  "w",
-  "w's",
-  "w.",
-  "w/o",
-  "wait",
-  "waiting",
-  "warm",
-  "warmth",
-  "was",
-  "wash",
-  "wash.",
-  "water",
-  "way",
-  "we",
-  "weather",
-  "weatherman",
-  "wed",
-  "weigh",
-  "weighed",
-  "weighs",
-  "weight",
-  "wel",
-  "went",
-  "wer",
-  "were",
-  "what",
-  "what's",
-  "what\u2019s",
-  "when",
-  "when's",
-  "when\u2019s",
-  "where",
-  "where's",
-  "where\u2019s",
-  "which",
-  "white",
-  "who",
-  "who's",
-  "who\u2019s",
-  "why",
-  "why's",
-  "why\u2019s",
-  "will",
-  "wine",
-  "winter",
-  "wire",
-  "wis",
-  "wis.",
-  "with",
-  "without",
-  "wo",
-  "words",
-  "would",
-  "w\u2019s",
-  "x",
-  "x'",
-  "x'x",
-  "x'xxxx",
-  "x.",
-  "x.X",
-  "x.d",
-  "x.x",
-  "x.x.",
-  "x/x",
-  "xD",
-  "xDD",
-  "xX",
-  "xXX",
-  "x_X",
-  "x_d",
-  "x_x",
-  "xam",
-  "xd",
-  "xdd",
-  "xit",
-  "xx",
-  "xx'",
-  "xx'x",
-  "xx'xx",
-  "xx.",
-  "xxd",
-  "xxx",
-  "xxx'x",
-  "xxx/xx",
-  "xxxx",
-  "xxxx'",
-  "xxxx'x",
-  "xxxx\u2019",
-  "xxxx\u2019x",
-  "xxx\u00b7X.",
-  "xxx\u00b7x.",
-  "xxx\u2019x",
-  "xx\u2019",
-  "xx\u2019x",
-  "xx\u2019xx",
-  "x\u2019",
-  "x\u2019x",
-  "x\u2019xxxx",
-  "x\ufe35x",
-  "y",
-  "y'",
-  "y's",
-  "y.",
-  "you",
-  "your",
-  "y\u2019",
-  "y\u2019s",
-  "z",
-  "z.",
-  "zed",
-  "zer",
-  "zero",
-  "zes",
-  "zip",
-  "zipline",
-  "zle",
-  "|",
-  "}",
-  "\u00a0",
-  "\u00ac",
-  "\u00ac_\u00ac",
-  "\u00af",
-  "\u00af\\(x)/\u00af",
-  "\u00af\\(\u30c4)/\u00af",
-  "\u00b0",
-  "\u00b0C.",
-  "\u00b0F.",
-  "\u00b0K.",
-  "\u00b0X.",
-  "\u00b0c.",
-  "\u00b0f.",
-  "\u00b0k.",
-  "\u00b0x.",
-  "\u00b7K.",
-  "\u00b7k.",
-  "\u00d7",
-  "\u00e4",
-  "\u00e4.",
-  "\u00f6",
-  "\u00f6.",
-  "\u00fc",
-  "\u00fc.",
-  "\u0ca0",
-  "\u0ca0_\u0ca0",
-  "\u0ca0\ufe35\u0ca0",
-  "\u2014",
-  "\u2018",
-  "\u2018S",
-  "\u2018X",
-  "\u2018s",
-  "\u2018x",
-  "\u2019",
-  "\u2019-(",
-  "\u2019-)",
-  "\u2019Cause",
-  "\u2019Cos",
-  "\u2019Coz",
-  "\u2019Cuz",
-  "\u2019S",
-  "\u2019X",
-  "\u2019Xxx",
-  "\u2019Xxxxx",
-  "\u2019am",
-  "\u2019bout",
-  "\u2019cause",
-  "\u2019cos",
-  "\u2019coz",
-  "\u2019cuz",
-  "\u2019d",
-  "\u2019em",
-  "\u2019ll",
-  "\u2019m",
-  "\u2019nuff",
-  "\u2019re",
-  "\u2019s",
-  "\u2019ve",
-  "\u2019x",
-  "\u2019xx",
-  "\u2019xxx",
-  "\u2019xxxx",
-  "\u2019y",
-  "\u2019\u2019",
-  "\u2501",
-  "\u253b",
-  "\u253b\u2501\u253b",
-  "\u256f",
-  "\u25a1",
-  "\ufe35",
-  "\uff09"
-]
+version https://git-lfs.github.com/spec/v1
+oid sha256:57cf1e27e8783cbb030e434d33c3b2f1d4db5a9e85646f57f6f6952d3f629b84
+size 11147861

vocab/vectors.cfg

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