add tokenizer

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": "/home/alce/.cache/huggingface/transformers/7d9fafaef70ad6beebafc62228f005fd41f80cd8194d66f335f3fc804fa045f3.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd", "tokenizer_file": null, "name_or_path": "facebook/wav2vec2-large-robust-ft-swbd-300h", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "E": 5, "T": 6, "O": 7, "A": 8, "I": 9, "N": 10, "H": 11, "S": 12, "R": 13, "L": 14, "D": 15, "U": 16, "Y": 17, "W": 18, "M": 19, "C": 20, "G": 21, "F": 22, "P": 23, "B": 24, "K": 25, "'": 26, "V": 27, "J": 28, "X": 29, "Q": 30, "Z": 31}