ccoreilly
commited on
Commit
•
4f89a19
0
Parent(s):
Initial commit
Browse files- preprocessor_config.json +8 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
preprocessor_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_size": 1,
|
4 |
+
"padding_side": "right",
|
5 |
+
"padding_value": 0.0,
|
6 |
+
"return_attention_mask": true,
|
7 |
+
"sampling_rate": 16000
|
8 |
+
}
|
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": "|"}
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"-": 0, "h": 1, "c": 2, "b": 3, "é": 4, "e": 5, "x": 6, "r": 7, "'": 8, "o": 9, "j": 10, "a": 11, "è": 12, "ó": 13, "ç": 15, "ï": 16, "s": 17, "f": 18, "ú": 19, "g": 20, "q": 21, "·": 22, "u": 23, "n": 24, "y": 25, "í": 26, "à": 27, "k": 28, "ü": 29, "w": 30, "v": 31, "ò": 32, "p": 33, "t": 34, "m": 35, "z": 36, "d": 37, "i": 38, "l": 39, "|": 14, "[UNK]": 40, "[PAD]": 41}
|