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": "/root/.cache/huggingface/transformers/a803f23f1afc428695542b16e67d92127ae59529b524e83b04b46e96c24e1dd5.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd", "tokenizer_file": null, "name_or_path": "lgris/bp_400h_xlsr2_300M", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"<s>": 1, "<pad>": 0, "</s>": 2, "<unk>": 3, "|": 4, "a": 5, "e": 6, "o": 7, "s": 8, "r": 9, "i": 10, "n": 11, "m": 12, "d": 13, "t": 14, "u": 15, "c": 16, "l": 17, "p": 18, "v": 19, "q": 20, "g": 21, "f": 22, "h": 23, "b": 24, "ã": 25, "é": 26, "ç": 27, "á": 28, "z": 29, "j": 30, "í": 31, "ê": 32, "x": 33, "ó": 34, "-": 35, "õ": 36, "ú": 37, "à": 38, "ô": 39, "â": 40, "k": 41, "y": 42, "w": 43}