add tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 31,
+  "<s>": 30
+}

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 +1,12 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "name_or_path": "./",
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,32 @@
+{
+  "'": 27,
+  "[PAD]": 29,
+  "[UNK]": 28,
+  "a": 6,
+  "b": 10,
+  "c": 20,
+  "d": 11,
+  "e": 24,
+  "f": 14,
+  "g": 2,
+  "h": 26,
+  "i": 12,
+  "j": 17,
+  "k": 0,
+  "l": 19,
+  "m": 25,
+  "n": 3,
+  "o": 5,
+  "p": 7,
+  "q": 22,
+  "r": 18,
+  "s": 16,
+  "t": 23,
+  "u": 4,
+  "v": 13,
+  "w": 21,
+  "x": 15,
+  "y": 9,
+  "z": 1,
+  "|": 8
+}