add tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"ö": 0, "g": 1, "p": 2, "ä": 3, "s": 4, "t": 5, "w": 6, "n": 7, "e": 8, "b": 9, "h": 10, "m": 12, "c": 13, "l": 14, "j": 15, "x": 16, "z": 17, "y": 18, "d": 19, "f": 20, "ü": 21, "v": 22, "k": 23, "i": 24, "r": 25, "u": 26, "q": 27, "a": 28, "o": 29, "|": 11, "[UNK]": 30, "[PAD]": 31}
|