Hugging Face's logo

FireRedTeam
/
FireRedPunc

Automatic Speech Recognition
Transformers
English
Chinese
Punctuation-Restoration
Punctuation-Prediction
Token Classification
BERT
LERT
audio
asr
Model card Files
xet
Community
FireRedTeam commited on
Commit
abeb0ce
·
verified ·
1 Parent(s): 9c16048

Init

Browse files
Files changed (13) hide show
  1. chinese-bert-wwm-ext_vocab.txt +0 -0
  2. chinese-lert-base/.gitattributes +33 -0
  3. chinese-lert-base/README.md +13 -0
  4. chinese-lert-base/added_tokens.json +1 -0
  5. chinese-lert-base/config.json +30 -0
  6. chinese-lert-base/pytorch_model.bin +3 -0
  7. chinese-lert-base/special_tokens_map.json +1 -0
  8. chinese-lert-base/tf_model.h5 +3 -0
  9. chinese-lert-base/tokenizer.json +0 -0
  10. chinese-lert-base/tokenizer_config.json +1 -0
  11. chinese-lert-base/vocab.txt +0 -0
  12. model.pth.tar +3 -0
  13. out_dict +5 -0
chinese-bert-wwm-ext_vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
chinese-lert-base/.gitattributes ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ftz filter=lfs diff=lfs merge=lfs -text
6
+ *.gz filter=lfs diff=lfs merge=lfs -text
7
+ *.h5 filter=lfs diff=lfs merge=lfs -text
8
+ *.joblib filter=lfs diff=lfs merge=lfs -text
9
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
10
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
11
+ *.model filter=lfs diff=lfs merge=lfs -text
12
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
13
+ *.npy filter=lfs diff=lfs merge=lfs -text
14
+ *.npz filter=lfs diff=lfs merge=lfs -text
15
+ *.onnx filter=lfs diff=lfs merge=lfs -text
16
+ *.ot filter=lfs diff=lfs merge=lfs -text
17
+ *.parquet filter=lfs diff=lfs merge=lfs -text
18
+ *.pb filter=lfs diff=lfs merge=lfs -text
19
+ *.pickle filter=lfs diff=lfs merge=lfs -text
20
+ *.pkl filter=lfs diff=lfs merge=lfs -text
21
+ *.pt filter=lfs diff=lfs merge=lfs -text
22
+ *.pth filter=lfs diff=lfs merge=lfs -text
23
+ *.rar filter=lfs diff=lfs merge=lfs -text
24
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
25
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
26
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
27
+ *.tflite filter=lfs diff=lfs merge=lfs -text
28
+ *.tgz filter=lfs diff=lfs merge=lfs -text
29
+ *.wasm filter=lfs diff=lfs merge=lfs -text
30
+ *.xz filter=lfs diff=lfs merge=lfs -text
31
+ *.zip filter=lfs diff=lfs merge=lfs -text
32
+ *.zst filter=lfs diff=lfs merge=lfs -text
33
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
chinese-lert-base/README.md ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - zh
4
+ license: "apache-2.0"
5
+ ---
6
+ ### LERT
7
+ LERT is a linguistically-motivated pre-trained language model.
8
+
9
+ Further information: https://github.com/ymcui/LERT/blob/main/README_EN.md
10
+
11
+ - **LERT: A Linguistically-motivated Pre-trained Language Model**
12
+ - *Yiming Cui, Wanxiang Che, Shijin Wang, Ting Liu*
13
+ - Paper link: https://arxiv.org/abs/2211.05344
chinese-lert-base/added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
chinese-lert-base/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": ".",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "transformers_version": "4.16.2",
27
+ "type_vocab_size": 2,
28
+ "use_cache": true,
29
+ "vocab_size": 21128
30
+ }
chinese-lert-base/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4ef03ee5a6ea58f973a2fe8fce42ba5d1cb006e5646c5cb32d421e9934c242d
3
+ size 411618486
chinese-lert-base/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
chinese-lert-base/tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73f11254904af5e27531fcfe31bf1dc88018af79f476e35cfc2250f28e552872
3
+ size 475929984
chinese-lert-base/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
chinese-lert-base/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"init_inputs": []}
chinese-lert-base/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.pth.tar ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a69e465132c79f639ba5a057cf06c90b2d7e36e4bbea56225ece260dcd0b0d4
3
+ size 406788602
out_dict ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ <space> 0
2
+ ， 1
3
+ 。 2
4
+ ？ 3
5
+ ！ 4