Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 51,
+  "<s>": 50
+}

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 +1,13 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "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

@@ -0,0 +1,52 @@
+{
+  "\n": 0,
+  "\r": 1,
+  "[PAD]": 49,
+  "[UNK]": 48,
+  "a": 3,
+  "b": 4,
+  "c": 5,
+  "d": 6,
+  "e": 7,
+  "g": 8,
+  "h": 9,
+  "i": 10,
+  "j": 11,
+  "k": 12,
+  "l": 13,
+  "m": 14,
+  "n": 15,
+  "o": 16,
+  "p": 17,
+  "r": 18,
+  "s": 19,
+  "t": 20,
+  "u": 21,
+  "v": 22,
+  "w": 23,
+  "|": 2,
+  "´": 24,
+  "ð": 25,
+  "ŋ": 26,
+  "ɔ": 27,
+  "ə": 28,
+  "ɛ": 29,
+  "ɜ": 30,
+  "ɟ": 31,
+  "ɲ": 32,
+  "ɽ": 33,
+  "ɾ": 34,
+  "ʃ": 35,
+  "̀": 36,
+  "́": 37,
+  "̂": 38,
+  "̄": 39,
+  "̊": 40,
+  "̋": 41,
+  "̌": 42,
+  "̏": 43,
+  "̪": 44,
+  "̯": 45,
+  "̺": 46,
+  "͡": 47
+}