Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 61,
+  "<s>": 60
+}

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 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "58": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61": {
+      "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>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "eng_yor",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,64 @@
+{
+  "eng_yor": {
+    "\f": 0,
+    "0": 2,
+    "1": 3,
+    "2": 4,
+    "3": 5,
+    "4": 6,
+    "5": 7,
+    "6": 8,
+    "7": 9,
+    "8": 10,
+    "9": 11,
+    "[PAD]": 59,
+    "[UNK]": 58,
+    "a": 12,
+    "b": 13,
+    "c": 14,
+    "d": 15,
+    "e": 16,
+    "f": 17,
+    "g": 18,
+    "h": 19,
+    "i": 20,
+    "j": 21,
+    "k": 22,
+    "l": 23,
+    "m": 24,
+    "n": 25,
+    "o": 26,
+    "p": 27,
+    "q": 28,
+    "r": 29,
+    "s": 30,
+    "t": 31,
+    "u": 32,
+    "v": 33,
+    "w": 34,
+    "x": 35,
+    "y": 36,
+    "z": 37,
+    "|": 1,
+    " ": 38,
+    "à": 39,
+    "á": 40,
+    "è": 41,
+    "é": 42,
+    "ì": 43,
+    "í": 44,
+    "î": 45,
+    "ñ": 46,
+    "ò": 47,
+    "ó": 48,
+    "ù": 49,
+    "ú": 50,
+    "ń": 51,
+    "̀": 52,
+    "́": 53,
+    "ṣ": 54,
+    "ẹ": 55,
+    "ọ": 56,
+    "’": 57
+  }
+}