ntsema
/

wav2vec2-xlsr-53-espeak-cv-ft-evn2-ntsema-colab

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

ntsema commited on Nov 10, 2022

Commit

b0e9342

•

1 Parent(s): cedd29a

Upload tokenizer

Files changed (2) hide show

added_tokens.json +2 -2
vocab.json +17 -7

added_tokens.json CHANGED Viewed

@@ -1,4 +1,4 @@
 {
-  "</s>": 45,
-  "<s>": 44
 }

 {
+  "</s>": 55,
+  "<s>": 54
 }

vocab.json CHANGED Viewed

@@ -1,26 +1,39 @@
 {
-  "[PAD]": 43,
-  "[UNK]": 42,
   "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,
   "r": 17,
   "s": 18,
   "t": 19,
   "u": 20,
   "v": 21,
   "w": 22,
   "x": 23,
@@ -32,15 +45,12 @@
   "ɒ": 28,
   "ɔ": 29,
   "ə": 30,
   "ɣ": 31,
   "ɨ": 32,
   "ɲ": 33,
   "ʃ": 34,
   "ʒ": 35,
   "ʲ": 36,
-  "ː": 37,
-  "́": 38,
-  "̄": 39,
-  "͡": 40,
-  "χ": 41
 }

 {
+  "[PAD]": 53,
+  "[UNK]": 52,
   "a": 1,
+  "aː": 41,
+  "ā": 49,
   "b": 2,
   "c": 3,
   "d": 4,
+  "dʲ": 50,
   "e": 5,
+  "eː": 43,
   "f": 6,
   "g": 7,
   "h": 8,
   "i": 9,
+  "iː": 39,
   "j": 10,
   "k": 11,
   "l": 12,
   "m": 13,
+  "mʲ": 47,
   "n": 14,
+  "nʲ": 37,
+  "ń": 44,
   "o": 15,
+  "oː": 42,
   "p": 16,
   "r": 17,
   "s": 18,
+  "sʲ": 38,
   "t": 19,
+  "tʲ": 45,
+  "t͡ʃ": 46,
   "u": 20,
+  "uː": 40,
   "v": 21,
   "w": 22,
   "x": 23,
   "ɒ": 28,
   "ɔ": 29,
   "ə": 30,
+  "ə̄": 48,
   "ɣ": 31,
   "ɨ": 32,
   "ɲ": 33,
   "ʃ": 34,
   "ʒ": 35,
   "ʲ": 36,
+  "χ": 51
 }