Upload folder using huggingface_hub

README.md

@@ -1,3 +1,19 @@
----
-license: apache-2.0
----
+## PUNC-BERT
+
+This is a chinese-lert-base model finetuned for punctuation restoration, release mainly for [FireRedASR](https://github.com/FireRedTeam/FireRedASR) postprocessing.
+
+Model restores the following punctuations -- [， 。 ？ ！]
+
+### License
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+   http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

chinese-lert-base-tokenizer/README.md

@@ -0,0 +1,13 @@
+---
+language: 
+- zh
+license: "apache-2.0"
+---
+### LERT
+LERT is a linguistically-motivated pre-trained language model.
+
+Further information: https://github.com/ymcui/LERT/blob/main/README_EN.md
+
+- **LERT: A Linguistically-motivated Pre-trained Language Model**
+- *Yiming Cui, Wanxiang Che, Shijin Wang, Ting Liu*
+- Paper link: https://arxiv.org/abs/2211.05344

chinese-lert-base-tokenizer/added_tokens.json

@@ -0,0 +1 @@
+{}

chinese-lert-base-tokenizer/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": ".",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.16.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

chinese-lert-base-tokenizer/special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

chinese-lert-base-tokenizer/tokenizer_config.json

@@ -0,0 +1 @@
+{"init_inputs": []}

model.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e94b720e3e53d0a113ff35cc60fbdb9bb78b92f55b895a246fb6a9ae6a9cae
+size 1220496325

out_dict

@@ -0,0 +1,5 @@
+<space> 0
+， 1
+。 2
+？ 3
+！ 4