mortimerme commited on
Commit
f476aa8
·
1 Parent(s): e4f9801

Upload 3 files

Browse files
Files changed (4) hide show
  1. .gitattributes +1 -0
  2. puntc/config.yaml +46 -0
  3. puntc/model.onnx +3 -0
  4. puntc/tokens.json +0 -0
.gitattributes CHANGED
@@ -1,2 +1,3 @@
1
  *.7z filter=lfs diff=lfs merge=lfs -text
2
  whisper-cpp-win32.zip filter=lfs diff=lfs merge=lfs -text
 
 
1
  *.7z filter=lfs diff=lfs merge=lfs -text
2
  whisper-cpp-win32.zip filter=lfs diff=lfs merge=lfs -text
3
+ puntc/model.onnx filter=lfs diff=lfs merge=lfs -text
puntc/config.yaml ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model: CTTransformer
2
+ model_conf:
3
+ ignore_id: 0
4
+ embed_unit: 256
5
+ att_unit: 256
6
+ dropout_rate: 0.1
7
+ punc_list:
8
+ - <unk>
9
+ - _
10
+ - ,
11
+ - 。
12
+ - ?
13
+ - 、
14
+ punc_weight:
15
+ - 1.0
16
+ - 1.0
17
+ - 1.0
18
+ - 1.0
19
+ - 1.0
20
+ - 1.0
21
+ sentence_end_id: 3
22
+
23
+ encoder: SANMEncoder
24
+ encoder_conf:
25
+ input_size: 256
26
+ output_size: 256
27
+ attention_heads: 8
28
+ linear_units: 1024
29
+ num_blocks: 4
30
+ dropout_rate: 0.1
31
+ positional_dropout_rate: 0.1
32
+ attention_dropout_rate: 0.0
33
+ input_layer: pe
34
+ pos_enc_class: SinusoidalPositionEncoder
35
+ normalize_before: true
36
+ kernel_size: 11
37
+ sanm_shfit: 0
38
+ selfattention_layer_type: sanm
39
+ padding_idx: 0
40
+
41
+ tokenizer: CharTokenizer
42
+ tokenizer_conf:
43
+ unk_symbol: <unk>
44
+
45
+
46
+
puntc/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e93593a6dbd69a07f8734ef269dbe861a379755f8d1c8354719432116f2c44bd
3
+ size 294372519
puntc/tokens.json ADDED
The diff for this file is too large to render. See raw diff