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