Upload lm-boosted decoder
Browse files- added_tokens.json +4 -0
- language_model/5gram.bin +3 -0
- language_model/attrs.json +1 -0
- language_model/unigrams.txt +0 -0
- preprocessor_config.json +1 -0
- special_tokens_map.json +22 -1
- tokenizer_config.json +13 -1
- vocab.json +42 -1
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 41,
|
3 |
+
"<s>": 40
|
4 |
+
}
|
language_model/5gram.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:321909dfb868371497164452e3e54a440816d1e19cbc1b9d7ed1b312a5affc44
|
3 |
+
size 451748395
|
language_model/attrs.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}
|
language_model/unigrams.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
preprocessor_config.json
CHANGED
@@ -4,6 +4,7 @@
|
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
|
|
7 |
"return_attention_mask": true,
|
8 |
"sampling_rate": 16000
|
9 |
}
|
|
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
8 |
"return_attention_mask": true,
|
9 |
"sampling_rate": 16000
|
10 |
}
|
special_tokens_map.json
CHANGED
@@ -1 +1,22 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "</s>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
+
],
|
18 |
+
"bos_token": "<s>",
|
19 |
+
"eos_token": "</s>",
|
20 |
+
"pad_token": "[PAD]",
|
21 |
+
"unk_token": "[UNK]"
|
22 |
+
}
|
tokenizer_config.json
CHANGED
@@ -1 +1,13 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"name_or_path": "RuiqianLi/Malaya-speech_fine-tune_realcase_27_Jun",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
8 |
+
"replace_word_delimiter_char": " ",
|
9 |
+
"special_tokens_map_file": "/root/.cache/huggingface/transformers/ec2735aef38f066d30261838cf7f6ccd1b63d4944a368dc7607b1429f9d64abb.a21d51735cf8667bcd610f057e88548d5d6a381401f6b4501a8bc6c1a9dc8498",
|
10 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
11 |
+
"unk_token": "[UNK]",
|
12 |
+
"word_delimiter_token": "|"
|
13 |
+
}
|
vocab.json
CHANGED
@@ -1 +1,42 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"": 0,
|
3 |
+
"0": 27,
|
4 |
+
"1": 28,
|
5 |
+
"2": 29,
|
6 |
+
"3": 30,
|
7 |
+
"4": 31,
|
8 |
+
"5": 32,
|
9 |
+
"6": 33,
|
10 |
+
"7": 34,
|
11 |
+
"8": 35,
|
12 |
+
"9": 36,
|
13 |
+
"[PAD]": 39,
|
14 |
+
"[UNK]": 38,
|
15 |
+
"a": 1,
|
16 |
+
"b": 2,
|
17 |
+
"c": 3,
|
18 |
+
"d": 4,
|
19 |
+
"e": 5,
|
20 |
+
"f": 6,
|
21 |
+
"g": 7,
|
22 |
+
"h": 8,
|
23 |
+
"i": 9,
|
24 |
+
"j": 10,
|
25 |
+
"k": 11,
|
26 |
+
"l": 12,
|
27 |
+
"m": 13,
|
28 |
+
"n": 14,
|
29 |
+
"o": 15,
|
30 |
+
"p": 16,
|
31 |
+
"q": 17,
|
32 |
+
"r": 18,
|
33 |
+
"s": 19,
|
34 |
+
"t": 20,
|
35 |
+
"u": 21,
|
36 |
+
"v": 22,
|
37 |
+
"w": 23,
|
38 |
+
"x": 24,
|
39 |
+
"y": 25,
|
40 |
+
"z": 26,
|
41 |
+
"|": 37
|
42 |
+
}
|