Upload lm-boosted decoder new
Browse files- alphabet.json +1 -0
- language_model/5gram_correct.arpa +0 -0
- language_model/attrs.json +1 -0
- language_model/unigrams.txt +27 -0
- preprocessor_config.json +1 -1
- special_tokens_map.json +14 -0
- tokenizer_config.json +2 -2
alphabet.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"labels": [" ", "c", "h", "k", "o", "s", "t", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
|
language_model/5gram_correct.arpa
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
</s>
|
2 |
+
<s>
|
3 |
+
c
|
4 |
+
c.
|
5 |
+
ch
|
6 |
+
ck
|
7 |
+
ck.
|
8 |
+
cs
|
9 |
+
cs.
|
10 |
+
h
|
11 |
+
h.
|
12 |
+
k
|
13 |
+
k.
|
14 |
+
kh
|
15 |
+
kh.
|
16 |
+
o
|
17 |
+
o.
|
18 |
+
s
|
19 |
+
s.
|
20 |
+
sh
|
21 |
+
sh.
|
22 |
+
sk
|
23 |
+
skh
|
24 |
+
ss
|
25 |
+
st
|
26 |
+
t
|
27 |
+
t.
|
preprocessor_config.json
CHANGED
@@ -4,7 +4,7 @@
|
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
7 |
-
"processor_class": "
|
8 |
"return_attention_mask": false,
|
9 |
"sampling_rate": 16000
|
10 |
}
|
|
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
8 |
"return_attention_mask": false,
|
9 |
"sampling_rate": 16000
|
10 |
}
|
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
@@ -2,9 +2,9 @@
|
|
2 |
"bos_token": "<s>",
|
3 |
"do_lower_case": false,
|
4 |
"eos_token": "</s>",
|
5 |
-
"name_or_path": "ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-v2",
|
6 |
"pad_token": "[PAD]",
|
7 |
-
"processor_class": "
|
8 |
"replace_word_delimiter_char": " ",
|
9 |
"special_tokens_map_file": null,
|
10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"do_lower_case": false,
|
4 |
"eos_token": "</s>",
|
5 |
+
"name_or_path": "gary109/ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-v2",
|
6 |
"pad_token": "[PAD]",
|
7 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
8 |
"replace_word_delimiter_char": " ",
|
9 |
"special_tokens_map_file": null,
|
10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|