add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 31, "</s>": 32}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

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": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"g": 0, "k": 1, "o": 2, "l": 4, "m": 5, "u": 6, "v": 7, "s": 8, "i": 9, "n": 10, "j": 11, "w": 12, "ô": 13, "f": 14, "̈": 15, "a": 16, "é": 17, "b": 18, "t": 19, "r": 20, "z": 21, "ñ": 22, "h": 23, "̃": 24, "p": 25, "y": 26, "e": 27, "d": 28, "|": 3, "[UNK]": 29, "[PAD]": 30}