add tokenizer

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 +1,12 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "name_or_path": "sanchit-gandhi/wav2vec2_ctc_tedlium_tokenizer",
+  "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 +1,36 @@
+{
+  "'": 14,
+  "<": 27,
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3,
+  ">": 20,
+  "a": 16,
+  "b": 22,
+  "c": 15,
+  "d": 6,
+  "e": 11,
+  "f": 25,
+  "g": 31,
+  "h": 13,
+  "i": 29,
+  "j": 18,
+  "k": 17,
+  "l": 26,
+  "m": 5,
+  "n": 23,
+  "o": 19,
+  "p": 33,
+  "q": 7,
+  "r": 8,
+  "s": 28,
+  "t": 21,
+  "u": 30,
+  "v": 9,
+  "w": 12,
+  "x": 4,
+  "y": 24,
+  "z": 32,
+  "|": 10
+}