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 +1,10 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,45 @@
+{
+  "C": 6,
+  "J": 35,
+  "O": 23,
+  "W": 11,
+  "Y": 18,
+  "[PAD]": 41,
+  "[UNK]": 40,
+  "b": 22,
+  "d": 25,
+  "e": 1,
+  "f": 10,
+  "g": 4,
+  "h": 30,
+  "i": 27,
+  "j": 33,
+  "k": 28,
+  "l": 38,
+  "m": 39,
+  "n": 20,
+  "o": 19,
+  "p": 21,
+  "s": 14,
+  "t": 12,
+  "u": 29,
+  "v": 2,
+  "w": 37,
+  "z": 0,
+  "|": 42,
+  "æ": 34,
+  "ð": 13,
+  "ŋ": 32,
+  "ɑ": 3,
+  "ɔ": 16,
+  "ə": 31,
+  "ɛ": 15,
+  "ɝ": 17,
+  "ɪ": 36,
+  "ɹ": 24,
+  "ʃ": 7,
+  "ʊ": 26,
+  "ʌ": 5,
+  "ʒ": 8,
+  "θ": 9
+}