Upload tokenizer

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
-base_model: mattbonnell/wav2vec2-base-wonders-phonemes
 tags:
 - generated_from_trainer
+base_model: mattbonnell/wav2vec2-base-wonders-phonemes
 datasets:
 - transcribed_calls
 model-index:

vocab.json

@@ -1,52 +1,52 @@
 {
   "[PAD]": 49,
   "[UNK]": 48,
-  "a": 29,
-  "b": 10,
-  "c": 34,
-  "d": 17,
-  "e": 33,
-  "f": 31,
-  "h": 11,
-  "i": 24,
-  "j": 42,
-  "k": 20,
-  "l": 30,
-  "m": 7,
-  "n": 35,
-  "o": 5,
-  "p": 40,
-  "r": 18,
-  "s": 37,
-  "t": 43,
-  "u": 14,
-  "v": 45,
-  "w": 23,
-  "y": 2,
-  "z": 12,
-  "|": 19,
-  "æ": 47,
-  "ð": 26,
-  "ŋ": 27,
-  "ɐ": 1,
-  "ɑ": 38,
-  "ɔ": 32,
-  "ə": 44,
-  "ɚ": 0,
-  "ɛ": 41,
-  "ɜ": 46,
-  "ɡ": 36,
-  "ɣ": 6,
-  "ɪ": 25,
-  "ɹ": 8,
-  "ɾ": 3,
-  "ʃ": 15,
-  "ʊ": 13,
-  "ʌ": 21,
-  "ʒ": 39,
-  "ʔ": 9,
-  "ː": 22,
-  "̩": 28,
-  "θ": 16,
-  "ᵻ": 4
+  "a": 0,
+  "b": 21,
+  "c": 43,
+  "d": 46,
+  "e": 7,
+  "f": 3,
+  "h": 27,
+  "i": 44,
+  "j": 31,
+  "k": 14,
+  "l": 29,
+  "m": 22,
+  "n": 24,
+  "o": 12,
+  "p": 9,
+  "r": 15,
+  "s": 17,
+  "t": 6,
+  "u": 33,
+  "v": 2,
+  "w": 8,
+  "y": 18,
+  "z": 1,
+  "|": 42,
+  "æ": 28,
+  "ð": 19,
+  "ŋ": 20,
+  "ɐ": 47,
+  "ɑ": 32,
+  "ɔ": 35,
+  "ə": 10,
+  "ɚ": 16,
+  "ɛ": 4,
+  "ɜ": 38,
+  "ɡ": 37,
+  "ɣ": 41,
+  "ɪ": 5,
+  "ɹ": 11,
+  "ɾ": 40,
+  "ʃ": 26,
+  "ʊ": 23,
+  "ʌ": 25,
+  "ʒ": 13,
+  "ʔ": 34,
+  "ː": 45,
+  "̩": 39,
+  "θ": 36,
+  "ᵻ": 30
 }