Upload lm-boosted decoder
Browse files- alphabet.json +1 -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 +28 -4
- tokenizer_config.json +1 -0
alphabet.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"labels": [" ", "\u0901", "\u0902", "\u0905", "\u0906", "\u0907", "\u0908", "\u0909", "\u090a", "\u090b", "\u090f", "\u0910", "\u0911", "\u0913", "\u0914", "\u0915", "\u0916", "\u0917", "\u0918", "\u091a", "\u091b", "\u091c", "\u091d", "\u091e", "\u091f", "\u0920", "\u0921", "\u0922", "\u0923", "\u0924", "\u0925", "\u0926", "\u0927", "\u0928", "\u092a", "\u092b", "\u092c", "\u092d", "\u092e", "\u092f", "\u0930", "\u0932", "\u0933", "\u0935", "\u0936", "\u0937", "\u0938", "\u0939", "\u093c", "\u093e", "\u093f", "\u0940", "\u0941", "\u0942", "\u0943", "\u0945", "\u0947", "\u0948", "\u0949", "\u094b", "\u094c", "\u094d", "\u2047", "", "<s>", "</s>", "\u2047", ""], "is_bpe": false}
|
language_model/5gram.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5189fbfb19e3a6238ef077ff0338b9d64ecd18f3521086cae0be79eec6927385
|
3 |
+
size 1962095
|
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
@@ -1,6 +1,30 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
}
|
tokenizer_config.json
CHANGED
@@ -55,6 +55,7 @@
|
|
55 |
"eos_token": "</s>",
|
56 |
"model_max_length": 1000000000000000019884624838656,
|
57 |
"pad_token": "<pad>",
|
|
|
58 |
"replace_word_delimiter_char": " ",
|
59 |
"target_lang": null,
|
60 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
55 |
"eos_token": "</s>",
|
56 |
"model_max_length": 1000000000000000019884624838656,
|
57 |
"pad_token": "<pad>",
|
58 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
59 |
"replace_word_delimiter_char": " ",
|
60 |
"target_lang": null,
|
61 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|