Upload processor

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -1,6 +1,6 @@
 {
   "bos_token": "<s>",
   "eos_token": "</s>",
-  "pad_token": "[PAD]",
-  "unk_token": "[UNK]"
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,48 +1,49 @@
 {
   "added_tokens_decoder": {
-    "54": {
-      "content": "[UNK]",
+    "0": {
+      "content": "<pad>",
       "lstrip": true,
       "normalized": false,
       "rstrip": true,
       "single_word": false,
       "special": false
     },
-    "55": {
-      "content": "[PAD]",
+    "1": {
+      "content": "<s>",
       "lstrip": true,
       "normalized": false,
       "rstrip": true,
       "single_word": false,
       "special": false
     },
-    "56": {
-      "content": "<s>",
-      "lstrip": false,
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "57": {
-      "content": "</s>",
-      "lstrip": false,
+    "3": {
+      "content": "<unk>",
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
-      "special": true
+      "special": false
     }
   },
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "do_lower_case": false,
   "eos_token": "</s>",
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
+  "pad_token": "<pad>",
+  "processor_class": "Wav2Vec2Processor",
   "replace_word_delimiter_char": " ",
-  "target_lang": null,
+  "target_lang": "eng",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
-  "unk_token": "[UNK]",
+  "unk_token": "<unk>",
   "word_delimiter_token": "|"
 }