Upload processor
Browse files- preprocessor_config.json +10 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +11 -0
- vocab.json +36 -0
preprocessor_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
+
"return_attention_mask": false,
|
9 |
+
"sampling_rate": 16000
|
10 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "[UNK]"
|
6 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"pad_token": "[PAD]",
|
6 |
+
"processor_class": "Wav2Vec2Processor",
|
7 |
+
"replace_word_delimiter_char": " ",
|
8 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
9 |
+
"unk_token": "[UNK]",
|
10 |
+
"word_delimiter_token": "|"
|
11 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
".": 0,
|
3 |
+
"[PAD]": 33,
|
4 |
+
"[UNK]": 32,
|
5 |
+
"a": 1,
|
6 |
+
"c": 2,
|
7 |
+
"e": 3,
|
8 |
+
"f": 4,
|
9 |
+
"g": 5,
|
10 |
+
"h": 6,
|
11 |
+
"i": 7,
|
12 |
+
"j": 8,
|
13 |
+
"k": 9,
|
14 |
+
"l": 10,
|
15 |
+
"m": 11,
|
16 |
+
"n": 12,
|
17 |
+
"o": 13,
|
18 |
+
"p": 14,
|
19 |
+
"r": 15,
|
20 |
+
"s": 16,
|
21 |
+
"t": 17,
|
22 |
+
"u": 18,
|
23 |
+
"w": 19,
|
24 |
+
"z": 20,
|
25 |
+
"|": 31,
|
26 |
+
"ŋ": 21,
|
27 |
+
"ɑ": 22,
|
28 |
+
"ɓ": 23,
|
29 |
+
"ɔ": 24,
|
30 |
+
"ɗ": 25,
|
31 |
+
"ə": 26,
|
32 |
+
"ɛ": 27,
|
33 |
+
"ɨ": 28,
|
34 |
+
"ɲ": 29,
|
35 |
+
"ʔ": 30
|
36 |
+
}
|