Upload tokenizer

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
-base_model: paruwka/wav2vec2-base-timit-demo-google-colab
 tags:
 - generated_from_trainer
+base_model: paruwka/wav2vec2-base-timit-demo-google-colab
 metrics:
 - wer
 model-index:

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 66,
-  "<s>": 65
+  "</s>": 69,
+  "<s>": 68
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "63": {
+    "66": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "64": {
+    "67": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "65": {
+    "68": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "66": {
+    "69": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,67 +1,70 @@
 {
-  "&": 42,
-  "'": 4,
-  "(": 32,
-  ")": 40,
-  "=": 19,
-  "[PAD]": 64,
-  "[UNK]": 63,
-  "a": 28,
-  "b": 18,
-  "c": 49,
-  "d": 54,
-  "e": 60,
-  "f": 36,
-  "g": 58,
-  "h": 11,
-  "i": 31,
-  "j": 2,
-  "k": 6,
-  "l": 14,
-  "m": 41,
-  "n": 22,
-  "o": 30,
-  "p": 35,
-  "q": 56,
-  "r": 53,
-  "s": 39,
-  "t": 43,
-  "u": 24,
-  "v": 20,
-  "w": 0,
-  "x": 50,
-  "y": 46,
-  "z": 55,
-  "|": 23,
-  "«": 33,
-  "»": 37,
-  "ß": 12,
-  "à": 44,
-  "á": 27,
-  "â": 61,
-  "ç": 62,
-  "è": 5,
-  "é": 17,
-  "ê": 26,
-  "ë": 34,
-  "î": 59,
-  "ï": 25,
-  "ó": 45,
-  "ô": 13,
-  "ö": 1,
-  "ù": 52,
-  "ú": 57,
-  "û": 48,
-  "ü": 9,
-  "ć": 47,
-  "ō": 15,
-  "œ": 21,
-  "ū": 16,
-  "̀": 8,
-  "́": 10,
-  "̂": 7,
-  "̧": 51,
-  "—": 3,
-  "’": 29,
-  "…": 38
+  "&": 28,
+  "'": 3,
+  "(": 13,
+  ")": 49,
+  "=": 54,
+  "[PAD]": 67,
+  "[UNK]": 66,
+  "a": 38,
+  "b": 8,
+  "c": 43,
+  "d": 21,
+  "e": 62,
+  "f": 57,
+  "g": 52,
+  "h": 44,
+  "i": 39,
+  "j": 60,
+  "k": 48,
+  "l": 19,
+  "m": 26,
+  "n": 15,
+  "o": 11,
+  "p": 17,
+  "q": 23,
+  "r": 14,
+  "s": 63,
+  "t": 2,
+  "u": 41,
+  "v": 30,
+  "w": 51,
+  "x": 20,
+  "y": 36,
+  "z": 18,
+  "|": 42,
+  "«": 46,
+  "»": 29,
+  "ß": 53,
+  "à": 59,
+  "á": 32,
+  "â": 55,
+  "ç": 24,
+  "è": 27,
+  "é": 16,
+  "ê": 6,
+  "ë": 5,
+  "î": 7,
+  "ï": 45,
+  "ó": 56,
+  "ô": 33,
+  "ö": 61,
+  "ø": 40,
+  "ù": 58,
+  "ú": 9,
+  "û": 47,
+  "ü": 34,
+  "ć": 4,
+  "ē": 0,
+  "ō": 22,
+  "œ": 10,
+  "š": 31,
+  "ū": 37,
+  "̀": 65,
+  "́": 35,
+  "̂": 12,
+  "̧": 64,
+  "—": 25,
+  "’": 50,
+  "…": 1
 }