Commit
•
264e19e
1
Parent(s):
b0c29d0
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>": 38, "</s>": 39}
|
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": "/root/.cache/huggingface/transformers/4eef8edb189e36dbc4815945af4d86921151e2b03804190038632ace066b655e.a21d51735cf8667bcd610f057e88548d5d6a381401f6b4501a8bc6c1a9dc8498", "tokenizer_file": null, "name_or_path": "anuragshas/wav2vec2-large-xlsr-53-rm-vallader", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"ê": 0, "ï": 1, "â": 2, "z": 3, "k": 4, "x": 5, "ö": 6, "s": 7, "l": 8, "n": 9, "è": 10, "ò": 11, "f": 12, "h": 13, "d": 14, "c": 15, "r": 16, "q": 17, "p": 18, "g": 19, "t": 20, "m": 21, "ä": 22, "u": 23, "e": 24, "b": 25, "à": 26, "o": 27, "v": 28, "ü": 29, "y": 30, "w": 32, "j": 33, "a": 34, "i": 35, "|": 31, "[UNK]": 36, "[PAD]": 37}
|