Upload tokenizer

added_tokens.json

@@ -1 +1,4 @@
-{"<s>": 35, "</s>": 36}
+{
+  "</s>": 36,
+  "<s>": 35
+}

special_tokens_map.json

@@ -1 +1,6 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -1 +1,95 @@
-{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{
+  "added_tokens_decoder": {
+    "23": {
+      "content": "ɛ˞u",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "eɪ",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "aɪ",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "aʊ",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "ɔɪ",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "oʊ",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -1 +1,37 @@
-{"p": 0, "t": 1, "k": 2, "b": 3, "d": 4, "g": 5, "ɾ": 6, "ʔ": 7, "h": 8, "ʃ": 9, "ʒ": 10, "θ": 11, "ð": 12, "ŋ": 13, "j": 14, "w": 15, "i": 16, "ɪ": 17, "ɛ": 18, "æ": 19, "ʌ": 20, "ə": 21, "ɚ": 22, "ɛ˞u": 23, "ʊ": 24, "ɔ": 25, "ɑ": 26, "eɪ": 27, "aɪ": 28, "aʊ": 29, "ɔɪ": 30, "oʊ": 31, "[UNK]": 32, "[PAD]": 33, "|": 34}
+{
+  "[PAD]": 33,
+  "[UNK]": 32,
+  "aɪ": 28,
+  "aʊ": 29,
+  "b": 3,
+  "d": 4,
+  "eɪ": 27,
+  "g": 5,
+  "h": 8,
+  "i": 16,
+  "j": 14,
+  "k": 2,
+  "oʊ": 31,
+  "p": 0,
+  "t": 1,
+  "w": 15,
+  "|": 34,
+  "æ": 19,
+  "ð": 12,
+  "ŋ": 13,
+  "ɑ": 26,
+  "ɔ": 25,
+  "ɔɪ": 30,
+  "ə": 21,
+  "ɚ": 22,
+  "ɛ": 18,
+  "ɛ˞u": 23,
+  "ɪ": 17,
+  "ɾ": 6,
+  "ʃ": 9,
+  "ʊ": 24,
+  "ʌ": 20,
+  "ʒ": 10,
+  "ʔ": 7,
+  "θ": 11
+}