Upload 8 files
Browse files- config.yaml +0 -0
- configuration.json +20 -0
- example/punc_example.txt +3 -0
- fig/struct.png +0 -0
- model.onnx +3 -0
- model_quant.onnx +3 -0
- punc.yaml +28 -0
- tokens.txt +0 -0
config.yaml
ADDED
The diff for this file is too large to render.
See raw diff
|
|
configuration.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"framework": "pytorch",
|
3 |
+
"task" : "punctuation",
|
4 |
+
"model" : {
|
5 |
+
"type" : "generic-punc",
|
6 |
+
"punc_model_name" : "punc.pb",
|
7 |
+
"punc_model_config" : {
|
8 |
+
"type": "pytorch",
|
9 |
+
"code_base": "funasr",
|
10 |
+
"mode": "punc",
|
11 |
+
"lang": "zh-cn",
|
12 |
+
"batch_size": 1,
|
13 |
+
"punc_config": "punc.yaml",
|
14 |
+
"model": "damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
|
15 |
+
}
|
16 |
+
},
|
17 |
+
"pipeline": {
|
18 |
+
"type":"punc-inference"
|
19 |
+
}
|
20 |
+
}
|
example/punc_example.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
1 跨境河流是养育沿岸人民的生命之源长期以来为帮助下游地区防灾减灾中方技术人员在上游地区极为恶劣的自然条件下克服巨大困难甚至冒着生命危险向印方提供汛期水文资料处理紧急事件中方重视印方在跨境河流问题上的关切愿意进一步完善双方联合工作机制凡是中方能做的我们都会去做而且会做得更好我请印度朋友们放心中国在上游的任何开发利用都会经过科学规划和论证兼顾上下游的利益
|
2 |
+
2 从存储上来说仅仅是全景图片它就会是图片的四倍的容量然后全景的视频会是普通视频八倍的这个存储的容要求而三d的模型会是图片的十倍这都对我们今天运行在的云计算的平台存储的平台提出了更高的要求
|
3 |
+
3 那今天的会就到这里吧 happy new year 明年见
|
fig/struct.png
ADDED
model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ea12dbe78ad0ec44834d3bf4a43937a30f24431f8537fdd812a91eee8b6d0fa
|
3 |
+
size 292007354
|
model_quant.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77005fff17c29a5895118ebd59bfe0646424457d05892aa061ef88192640fc59
|
3 |
+
size 282622148
|
punc.yaml
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
init: null
|
2 |
+
model_conf:
|
3 |
+
ignore_id: 0
|
4 |
+
use_preprocessor: true
|
5 |
+
token_type: word
|
6 |
+
bpemodel: null
|
7 |
+
non_linguistic_symbols: null
|
8 |
+
cleaner: null
|
9 |
+
g2p: null
|
10 |
+
punctuation: target_delay
|
11 |
+
punctuation_conf:
|
12 |
+
pos_enc: sinusoidal
|
13 |
+
embed_unit: 256
|
14 |
+
att_unit: 256
|
15 |
+
head: 8
|
16 |
+
unit: 1024
|
17 |
+
layer: 4
|
18 |
+
dropout_rate: 0.1
|
19 |
+
gpu_id: 0
|
20 |
+
punc_list:
|
21 |
+
- <unk>
|
22 |
+
- _
|
23 |
+
- ','
|
24 |
+
- 。
|
25 |
+
- '?'
|
26 |
+
- 、
|
27 |
+
distributed: true
|
28 |
+
version: 0.1.7
|
tokens.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|