Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 38,
+  "<s>": 37
+}

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": "twi",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,41 @@
+{
+  "twi": {
+    "[PAD]": 36,
+    "[UNK]": 35,
+    "a": 1,
+    "b": 2,
+    "c": 3,
+    "d": 4,
+    "e": 5,
+    "f": 6,
+    "g": 7,
+    "h": 8,
+    "i": 9,
+    "j": 10,
+    "k": 11,
+    "l": 12,
+    "m": 13,
+    "n": 14,
+    "o": 15,
+    "p": 16,
+    "r": 17,
+    "s": 18,
+    "t": 19,
+    "u": 20,
+    "v": 21,
+    "w": 22,
+    "y": 23,
+    "z": 24,
+    "|": 0,
+    "á": 25,
+    "ã": 26,
+    "õ": 27,
+    "ĩ": 28,
+    "ũ": 29,
+    "ɔ": 30,
+    "ɛ": 31,
+    "ʹ": 32,
+    "́": 33,
+    "•": 34
+  }
+}