tok
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 |
+
{"c": 0, "ē": 1, "ā": 2, "d": 3, "j": 4, "p": 5, "š": 6, "u": 7, "-": 8, "ī": 9, "ķ": 10, "g": 11, "h": 13, "m": 14, "ū": 15, "a": 16, "r": 17, "s": 18, "ņ": 19, "l": 20, "č": 21, "x": 22, "n": 23, "o": 24, "ļ": 25, "e": 26, "f": 27, "v": 28, "ž": 29, "i": 30, "b": 31, "t": 32, "ģ": 33, "z": 34, "k": 35, "|": 12, "[UNK]": 36, "[PAD]": 37}
|