Upload tokenizer

special_tokens_map.json

@@ -1,5 +1,19 @@
 {
   "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
     {
       "content": "<s>",
       "lstrip": false,

tokenizer_config.json

@@ -1,12 +1,14 @@
 {
   "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
   "do_lower_case": false,
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
   "replace_word_delimiter_char": " ",
-  "special_tokens_map_file": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "tokenizer_file": null,
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"
 }