ntsema
/

wav2vec2-xlsr-53-espeak-cv-ft-bak4-ntsema-colab

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

ntsema commited on Nov 12, 2022

Commit

b82a113

•

1 Parent(s): 06c7d44

Upload tokenizer

Files changed (2) hide show

added_tokens.json +2 -2
vocab.json +38 -63

added_tokens.json CHANGED Viewed

@@ -1,4 +1,4 @@
 {
-  "</s>": 67,
-  "<s>": 66
 }

 {
+  "</s>": 42,
+  "<s>": 41
 }

vocab.json CHANGED Viewed

@@ -1,68 +1,43 @@
 {
-  "[PAD]": 65,
-  "[UNK]": 64,
   "a": 1,
   "b": 2,
-  "d": 3,
-  "e": 4,
-  "f": 5,
-  "g": 6,
-  "h": 7,
-  "i": 8,
-  "j": 9,
-  "k": 10,
-  "l": 11,
-  "m": 12,
-  "n": 13,
-  "o": 14,
-  "p": 15,
-  "q": 16,
-  "r": 17,
-  "s": 18,
-  "t": 19,
-  "u": 20,
-  "v": 21,
-  "w": 22,
-  "x": 23,
-  "z": 24,
   "|": 0,
-  "æ": 25,
-  "ð": 26,
-  "ø": 27,
-  "ü": 28,
-  "ŋ": 29,
-  "ɐ": 30,
-  "ɑ": 31,
-  "ɒ": 32,
-  "ɔ": 33,
-  "ɕ": 34,
-  "ə": 35,
-  "ɛ": 36,
-  "ɜ": 37,
-  "ɡ": 38,
-  "ɣ": 39,
-  "ɨ": 40,
-  "ɪ": 41,
-  "ɯ": 42,
-  "ɵ": 43,
-  "ɸ": 44,
-  "ʃ": 45,
-  "ʉ": 46,
-  "ʊ": 47,
-  "ʌ": 48,
-  "ʐ": 49,
-  "ʑ": 50,
-  "ʔ": 51,
-  "ː": 52,
-  "ˑ": 53,
-  "̆": 54,
-  "̈": 55,
-  "̞": 56,
-  "̟": 57,
-  "̠": 58,
-  "̥": 59,
-  "̬": 60,
-  "͡": 61,
-  "β": 62,
-  "θ": 63
 }

 {
+  "[PAD]": 40,
+  "[UNK]": 39,
   "a": 1,
   "b": 2,
+  "c": 3,
+  "d": 4,
+  "e": 5,
+  "f": 6,
+  "g": 7,
+  "h": 8,
+  "i": 9,
+  "j": 10,
+  "k": 11,
+  "l": 12,
+  "m": 13,
+  "n": 14,
+  "o": 15,
+  "p": 16,
+  "q": 17,
+  "r": 18,
+  "s": 19,
+  "t": 20,
+  "u": 21,
+  "v": 22,
+  "w": 23,
+  "x": 24,
+  "y": 25,
+  "z": 26,
   "|": 0,
+  "æ": 27,
+  "ð": 28,
+  "ü": 29,
+  "ŋ": 30,
+  "œ": 31,
+  "ə": 32,
+  "ɣ": 33,
+  "ʃ": 34,
+  "ʒ": 35,
+  "ʔ": 36,
+  "͡": 37,
+  "θ": 38
 }