Upload processor

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 44,
-  "<s>": 43
+  "</s>": 56,
+  "<s>": 55
 }

preprocessor_config.json

@@ -4,6 +4,7 @@
   "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 +1,14 @@
 {
   "added_tokens_decoder": {
-    "11": {
+    "6": {
+      "content": "c̭",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
       "content": "k̭",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "17": {
+    "21": {
       "content": "p̂",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +24,7 @@
       "single_word": false,
       "special": false
     },
-    "27": {
+    "34": {
       "content": "č̭",
       "lstrip": true,
       "normalized": false,
@@ -24,7 +32,7 @@
       "single_word": false,
       "special": false
     },
-    "41": {
+    "53": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -32,7 +40,7 @@
       "single_word": false,
       "special": false
     },
-    "42": {
+    "54": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -40,7 +48,7 @@
       "single_word": false,
       "special": false
     },
-    "43": {
+    "55": {
       "content": "<s>",
       "lstrip": false,
       "normalized": true,
@@ -48,7 +56,7 @@
       "single_word": false,
       "special": true
     },
-    "44": {
+    "56": {
       "content": "</s>",
       "lstrip": false,
       "normalized": true,

vocab.json

@@ -1,45 +1,57 @@
 {
   "-": 0,
-  "[PAD]": 42,
-  "[UNK]": 41,
-  "a": 1,
-  "b": 2,
-  "c": 3,
-  "d": 4,
-  "e": 5,
-  "f": 6,
-  "g": 7,
-  "h": 8,
-  "i": 9,
-  "j": 10,
-  "k̭": 11,
-  "l": 12,
-  "m": 13,
-  "n": 14,
-  "o": 15,
-  "p": 16,
-  "p̂": 17,
-  "r": 18,
-  "s": 19,
-  "t": 20,
-  "u": 21,
-  "v": 22,
-  "x": 23,
-  "y": 24,
-  "z": 25,
-  "č": 26,
-  "č̭": 27,
-  "š": 28,
-  "ž": 29,
-  "ǧ": 30,
-  "ə": 31,
-  "ʾ": 32,
-  "ˈ": 33,
-  "̀": 34,
-  "́": 35,
-  "̄": 36,
-  "̆": 37,
-  "ṱ": 38,
-  "⁺": 39,
-  "꞊": 40
+  "[": 1,
+  "[PAD]": 54,
+  "[UNK]": 53,
+  "]": 2,
+  "a": 3,
+  "b": 4,
+  "c": 5,
+  "c̭": 6,
+  "d": 7,
+  "e": 8,
+  "f": 9,
+  "g": 10,
+  "h": 11,
+  "i": 12,
+  "j": 13,
+  "k": 14,
+  "k̭": 15,
+  "l": 16,
+  "m": 17,
+  "n": 18,
+  "o": 19,
+  "p": 20,
+  "p̂": 21,
+  "r": 22,
+  "s": 23,
+  "t": 24,
+  "u": 25,
+  "v": 26,
+  "w": 27,
+  "x": 28,
+  "y": 29,
+  "z": 30,
+  "ã": 31,
+  "ü": 32,
+  "č": 33,
+  "č̭": 34,
+  "ı": 35,
+  "ŕ": 36,
+  "š": 37,
+  "ž": 38,
+  "ǘ": 39,
+  "ǜ": 40,
+  "ǧ": 41,
+  "ɑ": 42,
+  "ə": 43,
+  "ʾ": 44,
+  "ˈ": 45,
+  "̀": 46,
+  "́": 47,
+  "̄": 48,
+  "̆": 49,
+  "ṱ": 50,
+  "⁺": 51,
+  "꞊": 52
 }