Upload tokenizer

README.md

@@ -1,18 +1,18 @@
 ---
 license: apache-2.0
-base_model: facebook/wav2vec2-base
 tags:
 - generated_from_trainer
 datasets:
 - common_voice_7_0
 metrics:
 - wer
+base_model: facebook/wav2vec2-base
 model-index:
 - name: luganda_wav2vec2_ctc_tokenizer
   results:
   - task:
-      name: Automatic Speech Recognition
       type: automatic-speech-recognition
+      name: Automatic Speech Recognition
     dataset:
       name: common_voice_7_0
       type: common_voice_7_0
@@ -20,9 +20,9 @@ model-index:
       split: None
       args: lg
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 0.5608917697898251
+      name: Wer
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

added_tokens.json

@@ -1,6 +1,6 @@
 {
-  "</s>": 40,
-  "<s>": 39,
-  "[PAD]": 38,
-  "[UNK]": 37
+  "</s>": 32,
+  "<s>": 31,
+  "[PAD]": 30,
+  "[UNK]": 29
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "37": {
+    "29": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "38": {
+    "30": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,18 +16,18 @@
       "single_word": false,
       "special": false
     },
-    "39": {
+    "31": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "40": {
+    "32": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true

vocab.json

@@ -1,41 +1,33 @@
 {
-  "'": 20,
-  "[PAD]": 38,
-  "[UNK]": 37,
-  "`": 51,
-  "a": 12,
-  "b": 26,
-  "c": 7,
-  "d": 19,
-  "e": 1,
-  "f": 28,
-  "g": 6,
-  "h": 43,
-  "i": 0,
-  "j": 27,
-  "k": 31,
-  "l": 23,
-  "m": 37,
-  "n": 44,
-  "o": 48,
-  "p": 21,
-  "q": 35,
-  "r": 49,
-  "s": 46,
-  "t": 18,
-  "u": 25,
-  "v": 36,
-  "w": 4,
-  "x": 45,
-  "y": 42,
+  "'": 11,
+  "[PAD]": 30,
+  "[UNK]": 29,
+  "a": 22,
+  "b": 1,
+  "c": 4,
+  "d": 2,
+  "e": 21,
+  "f": 14,
+  "g": 27,
+  "h": 18,
+  "i": 23,
+  "j": 15,
+  "k": 16,
+  "l": 3,
+  "m": 7,
+  "n": 17,
+  "o": 8,
+  "p": 5,
+  "r": 26,
+  "s": 25,
+  "t": 30,
+  "u": 6,
+  "v": 9,
+  "w": 0,
+  "x": 13,
+  "y": 29,
   "z": 24,
-  "|": 52,
-  "`": 34,
-  "–": 39,
-  "—": 17,
-  "‘": 16,
-  "’": 47,
-  "“": 22,
-  "”": 15,
-  "‟": 38
+  "|": 28,
+  "‘": 10,
+  "’": 12
 }