tokenizer v2 - fix user defined symbols

README.md

@@ -88,7 +88,7 @@ config = {
     "split_by_whitespace": true,
     "model_prefix": "./spiece",
     "input_sentence_size": 4000000,
-    "user_defined_symbols": "(,),\",-,.,–,£"
+    "user_defined_symbols": "(,),-,.,–,£,।",
 }
 spm.SentencePieceTrainer.train(**config)
 ```

spiece.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0847b3d2eef4dca2710292d7d5f8046b58eea0e68d63de3d5738c4f7ddf7042
-size 1159342
+oid sha256:7adde7820956626ed2ab167049ffedaa4d293f8b072dcc8f055e68bb8450cd51
+size 1160663

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": true, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "tokenizer-bn-v0.0.1"}
+{"do_lower_case": true, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/content/drive/MyDrive/collaborative hub training/tokenizer/tokenizer_bn/oscar_wiki_bn_spm_unigram_4000000_2021_04_23_10_05_27/old"}