add tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 44,
+  "<s>": 43
+}

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token": "<s>",
+  "do_phonemize": false,
+  "eos_token": "</s>",
+  "name_or_path": "./vocab/",
+  "pad_token": "[PAD]",
+  "phone_delimiter_token": "|",
+  "phonemizer_backend": "espeak",
+  "phonemizer_lang": "en-us",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "Wav2Vec2PhonemeCTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": null
+}

vocab.json

@@ -0,0 +1,45 @@
+{
+  "A": 0,
+  "B": 1,
+  "BB": 2,
+  "CHh": 3,
+  "D": 4,
+  "DD": 5,
+  "E": 6,
+  "EO": 7,
+  "EU": 8,
+  "G": 9,
+  "GG": 10,
+  "H": 11,
+  "I": 12,
+  "J": 13,
+  "JJ": 14,
+  "Kh": 15,
+  "L": 16,
+  "M": 17,
+  "N": 18,
+  "NG": 19,
+  "O": 20,
+  "Ph": 21,
+  "R": 22,
+  "S": 23,
+  "SS": 24,
+  "Th": 25,
+  "U": 26,
+  "[PAD]": 42,
+  "[UNK]": 41,
+  "euI": 27,
+  "iA": 28,
+  "iE": 29,
+  "iEO": 30,
+  "iO": 31,
+  "iU": 32,
+  "k": 33,
+  "oA": 34,
+  "oE": 35,
+  "p": 36,
+  "t": 37,
+  "uEO": 38,
+  "uI": 39,
+  "|": 40
+}