Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "BOS",
+  "eos_token": "EOS",
+  "pad_token": "PAD",
+  "unk_token": "UNK"
+}

tokenizer.json

@@ -0,0 +1,125 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "UNK",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "PAD",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "BOS",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "EOS",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": {
+    "type": "Sequence",
+    "normalizers": [
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "\n"
+        },
+        "content": " UTT_BOUNDARY"
+      },
+      {
+        "type": "Strip",
+        "strip_left": true,
+        "strip_right": true
+      }
+    ]
+  },
+  "pre_tokenizer": {
+    "type": "Whitespace"
+  },
+  "post_processor": null,
+  "decoder": null,
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "UNK": 0,
+      "PAD": 1,
+      "BOS": 2,
+      "EOS": 3,
+      "WORD_BOUNDARY": 4,
+      "UTT_BOUNDARY": 5,
+      "aː": 6,
+      "ɾ": 7,
+      "r": 8,
+      "ɪ": 9,
+      "ɛ": 10,
+      "d": 11,
+      "s": 12,
+      "j": 13,
+      "a": 14,
+      "b": 15,
+      "iː": 16,
+      "k": 17,
+      "ʋ": 18,
+      "ɛː": 19,
+      "θ": 20,
+      "i": 21,
+      "l": 22,
+      "n": 23,
+      "uː": 24,
+      "ð": 25,
+      "ɡ": 26,
+      "ɔ": 27,
+      "h": 28,
+      "aʊ": 29,
+      "y": 30,
+      "m": 31,
+      "f": 32,
+      "ɔː": 33,
+      "x": 34,
+      "ɟ": 35,
+      "t": 36,
+      "eɪ": 37,
+      "oʊ": 38,
+      "p": 39,
+      "ŋ": 40,
+      "ɣ": 41,
+      "yː": 42,
+      "u": 43,
+      "ɪː": 44,
+      "œ": 45,
+      "aɪ": 46,
+      "ç": 47,
+      "ə": 48,
+      "øy": 49,
+      "c": 50,
+      "ɲ": 51,
+      "œː": 52,
+      "ɔɪ": 53
+    },
+    "unk_token": "UNK"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

vocab.json

@@ -0,0 +1 @@
+{"UNK":0,"PAD":1,"BOS":2,"EOS":3,"WORD_BOUNDARY":4,"UTT_BOUNDARY":5,"aː":6,"ɾ":7,"r":8,"ɪ":9,"ɛ":10,"d":11,"s":12,"j":13,"a":14,"b":15,"iː":16,"k":17,"ʋ":18,"ɛː":19,"θ":20,"i":21,"l":22,"n":23,"uː":24,"ð":25,"ɡ":26,"ɔ":27,"h":28,"aʊ":29,"y":30,"m":31,"f":32,"ɔː":33,"x":34,"ɟ":35,"t":36,"eɪ":37,"oʊ":38,"p":39,"ŋ":40,"ɣ":41,"yː":42,"u":43,"ɪː":44,"œ":45,"aɪ":46,"ç":47,"ə":48,"øy":49,"c":50,"ɲ":51,"œː":52,"ɔɪ":53}