patrickvonplaten
commited on
Commit
•
987b4d6
1
Parent(s):
fcf5b60
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>": 30, "</s>": 31}
|
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 |
+
{"b": 0, "a": 1, "s": 2, "f": 3, "c": 4, "m": 5, "l": 6, "p": 7, "t": 8, "u": 9, "i": 10, "j": 11, "y": 12, "d": 13, "n": 14, "e": 15, "q": 16, "k": 17, "o": 18, "r": 20, "'": 21, "x": 22, "z": 23, "h": 24, "w": 25, "g": 26, "v": 27, "|": 19, "[UNK]": 28, "[PAD]": 29}
|