Upload tokenizer

special_tokens_map.json

@@ -1 +1,20 @@
-{"bos_token": "<s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "</s>", "mask_token": "<special1>", "additional_special_tokens": ["<special0>", "<special1>", "<special2>", "<special3>", "<special4>", "<special5>", "<special6>", "<special7>", "<special8>", "<special9>"]}
+{
+  "additional_special_tokens": [
+    "<special0>",
+    "<special1>",
+    "<special2>",
+    "<special3>",
+    "<special4>",
+    "<special5>",
+    "<special6>",
+    "<special7>",
+    "<special8>",
+    "<special9>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "</s>",
+  "mask_token": "<special1>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -1 +1,28 @@
-{"unk_token": "<unk>", "bos_token": "<s>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "</s>", "mask_token": "<special1>", "additional_special_tokens": ["<special0>", "<special1>", "<special2>", "<special3>", "<special4>", "<special5>", "<special6>", "<special7>", "<special8>", "<special9>"], "lang2id": null, "id2lang": null, "do_lowercase_and_remove_accent": true, "do_lower_case": true, "keep_accents": true, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/export/home/lium/vpelloin/git/ghannay_slu_MEDIA_Eval/BERT/FineTune_FlauBERT/12-03-22_18-48/flaubert/flaubert_base_uncased/checkpoint-best/asr-ref", "tokenizer_class": "FlaubertTokenizer"}
+{
+  "additional_special_tokens": [
+    "<special0>",
+    "<special1>",
+    "<special2>",
+    "<special3>",
+    "<special4>",
+    "<special5>",
+    "<special6>",
+    "<special7>",
+    "<special8>",
+    "<special9>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "</s>",
+  "do_lower_case": true,
+  "id2lang": null,
+  "keep_accents": true,
+  "lang2id": null,
+  "mask_token": "<special1>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "FlaubertTokenizer",
+  "tokenizer_file": null,
+  "unk_token": "<unk>"
+}