Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "do_phonemize": false,
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "phone_delimiter_token": " ",
+  "phonemizer_backend": "espeak",
+  "phonemizer_lang": "en-us",
+  "return_attention_mask": false,
+  "tokenizer_class": "Wav2Vec2PhonemeCTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,60 @@
+{
+  "</s>": 53,
+  "<pad>": 56,
+  "<s>": 54,
+  "<unk>": 55,
+  "a": 47,
+  "aː": 25,
+  "b": 15,
+  "d": 26,
+  "e": 51,
+  "eʊ": 46,
+  "eː": 11,
+  "f": 8,
+  "h": 2,
+  "i": 29,
+  "iː": 42,
+  "j": 37,
+  "k": 16,
+  "l": 6,
+  "m": 28,
+  "n": 20,
+  "oː": 22,
+  "p": 24,
+  "r": 18,
+  "s": 1,
+  "t": 4,
+  "tʃ": 41,
+  "tʲ": 34,
+  "u": 36,
+  "uː": 52,
+  "v": 9,
+  "w": 39,
+  "x": 12,
+  "y": 23,
+  "yʊ": 40,
+  "z": 14,
+  "|": 57,
+  "øː": 33,
+  "ŋ": 30,
+  "œy": 32,
+  "ɑ": 7,
+  "ɑ̃": 50,
+  "ɔ": 10,
+  "ɔː": 27,
+  "ə": 3,
+  "ɛ": 19,
+  "ɛɪ": 13,
+  "ɛː": 45,
+  "ɡ": 48,
+  "ɣ": 5,
+  "ɪ": 0,
+  "ɪː": 17,
+  "ɲ": 43,
+  "ɵ": 38,
+  "ɾ": 44,
+  "ʃ": 31,
+  "ʋ": 21,
+  "ʌʊ": 35,
+  "ʒ": 49
+}