Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 72,
+  "<s>": 71
+}

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 +1,73 @@
+{
+  "$": 1,
+  "H": 2,
+  "O": 3,
+  "W": 4,
+  "[PAD]": 70,
+  "[UNK]": 69,
+  "a": 5,
+  "c": 6,
+  "e": 7,
+  "h": 8,
+  "l": 9,
+  "m": 10,
+  "o": 11,
+  "p": 12,
+  "t": 13,
+  "w": 14,
+  "x": 15,
+  "|": 0,
+  "ꯀ": 16,
+  "ꯁ": 17,
+  "ꯂ": 18,
+  "ꯃ": 19,
+  "ꯄ": 20,
+  "ꯅ": 21,
+  "ꯆ": 22,
+  "ꯇ": 23,
+  "ꯈ": 24,
+  "ꯉ": 25,
+  "ꯊ": 26,
+  "ꯋ": 27,
+  "ꯌ": 28,
+  "ꯍ": 29,
+  "ꯎ": 30,
+  "ꯏ": 31,
+  "ꯐ": 32,
+  "ꯑ": 33,
+  "ꯒ": 34,
+  "ꯔ": 35,
+  "ꯕ": 36,
+  "ꯖ": 37,
+  "ꯗ": 38,
+  "ꯘ": 39,
+  "ꯙ": 40,
+  "ꯚ": 41,
+  "ꯛ": 42,
+  "ꯜ": 43,
+  "ꯝ": 44,
+  "ꯞ": 45,
+  "ꯟ": 46,
+  "ꯠ": 47,
+  "ꯡ": 48,
+  "ꯢ": 49,
+  "ꯣ": 50,
+  "ꯤ": 51,
+  "ꯥ": 52,
+  "ꯦ": 53,
+  "ꯧ": 54,
+  "ꯨ": 55,
+  "ꯩ": 56,
+  "ꯪ": 57,
+  "꯭": 58,
+  "꯰": 59,
+  "꯱": 60,
+  "꯲": 61,
+  "꯳": 62,
+  "꯴": 63,
+  "꯵": 64,
+  "꯶": 65,
+  "꯷": 66,
+  "꯸": 67,
+  "꯹": 68
+}