Upload new lm-boosted decoder
Browse files- language_model/6gram.bin +3 -0
- language_model/attrs.json +1 -0
- language_model/unigrams.txt +3 -0
- special_tokens_map.json +14 -0
- tokenizer_config.json +1 -0
language_model/6gram.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:854863b2d7ef86d1dab687cbd0894c4ab048358de11058e3e9c2f47b5fca6170
|
3 |
+
size 8319130332
|
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
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f80a16e5bcddb0b96faa8311173b9595b5dcb6c87e9d8bcc139fe0ef88cc89c8
|
3 |
+
size 106370349
|
special_tokens_map.json
CHANGED
@@ -21,6 +21,20 @@
|
|
21 |
"rstrip": false,
|
22 |
"single_word": false
|
23 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
{
|
25 |
"content": "</s>",
|
26 |
"lstrip": false,
|
|
|
21 |
"rstrip": false,
|
22 |
"single_word": false
|
23 |
},
|
24 |
+
{
|
25 |
+
"content": "</s>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": true,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"content": "<s>",
|
33 |
+
"lstrip": false,
|
34 |
+
"normalized": true,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
},
|
38 |
{
|
39 |
"content": "</s>",
|
40 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -8,6 +8,7 @@
|
|
8 |
"replace_word_delimiter_char": " ",
|
9 |
"special_tokens_map_file": null,
|
10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
11 |
"unk_token": "[UNK]",
|
12 |
"word_delimiter_token": "|"
|
13 |
}
|
|
|
8 |
"replace_word_delimiter_char": " ",
|
9 |
"special_tokens_map_file": null,
|
10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
11 |
+
"trust_remote_code": false,
|
12 |
"unk_token": "[UNK]",
|
13 |
"word_delimiter_token": "|"
|
14 |
}
|