elisabethvonoswald
commited on
Commit
•
f2a7362
1
Parent(s):
bb5205a
add tokenizer
Browse files- added_tokens.json +1 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<s>": 40, "</s>": 41}
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
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
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
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
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"0": 1, "1": 2, "2": 3, "3": 4, "4": 5, "5": 6, "7": 7, "8": 8, "a": 9, "b": 10, "c": 11, "d": 12, "e": 13, "f": 14, "g": 15, "h": 16, "i": 17, "j": 18, "k": 19, "l": 20, "m": 21, "n": 22, "o": 23, "p": 24, "r": 25, "s": 26, "t": 27, "u": 28, "v": 29, "w": 30, "x": 31, "y": 32, "z": 33, "ß": 34, "ä": 35, "ö": 36, "ü": 37, "|": 0, "[UNK]": 38, "[PAD]": 39}
|