Upload processor

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "37": {
+    "31": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "38": {
+    "32": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,21 +16,21 @@
       "single_word": false,
       "special": false
     },
-    "39": {
+    "33": {
       "content": "<s>",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "40": {
+    "34": {
       "content": "</s>",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
-      "special": true
+      "special": false
     }
   },
   "bos_token": "<s>",
@@ -39,6 +39,7 @@
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json

@@ -1,7 +1,9 @@
 {
   "'": 1,
-  "[PAD]": 38,
-  "[UNK]": 37,
+  "</s>": 34,
+  "<s>": 33,
+  "[PAD]": 32,
+  "[UNK]": 31,
   "a": 2,
   "b": 3,
   "c": 4,
@@ -29,13 +31,7 @@
   "y": 26,
   "z": 27,
   "|": 0,
-  "à": 28,
-  "ô": 29,
-  "ú": 30,
-  "đ": 31,
-  "ạ": 32,
-  "ả": 33,
-  "ậ": 34,
-  "ắ": 35,
-  "ồ": 36
+  "ù": 28,
+  "ả": 29,
+  "ệ": 30
 }