Upload tokenizer

README.md

@@ -1,18 +1,18 @@
 ---
 license: mit
-base_model: facebook/w2v-bert-2.0
 tags:
 - generated_from_trainer
 datasets:
 - common_voice_16_0
 metrics:
 - wer
+base_model: facebook/w2v-bert-2.0
 model-index:
 - name: w2v-bert-2.0-swahili-colab-CV16.0_5epochs
   results:
   - task:
-      name: Automatic Speech Recognition
       type: automatic-speech-recognition
+      name: Automatic Speech Recognition
     dataset:
       name: common_voice_16_0
       type: common_voice_16_0
@@ -20,9 +20,9 @@ model-index:
       split: test
       args: sw
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 0.8218669188312941
+      name: Wer
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

added_tokens.json

@@ -1,4 +1,4 @@
 {
   "</s>": 70,
-  "<s>": 69
+  "[PAD]": 69
 }

tokenizer_config.json

@@ -1,14 +1,6 @@
 {
   "added_tokens_decoder": {
-    "67": {
-      "content": "[UNK]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "68": {
+    "69": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,14 +8,6 @@
       "single_word": false,
       "special": false
     },
-    "69": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
     "70": {
       "content": "</s>",
       "lstrip": false,
@@ -39,7 +23,6 @@
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "processor_class": "Wav2Vec2BertProcessor",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json

@@ -4,8 +4,8 @@
   "*": 3,
   "/": 4,
   "=": 5,
-  "[PAD]": 68,
-  "[UNK]": 67,
+  "[PAD]": 69,
+  "[UNK]": 69,
   "\\": 6,
   "_": 7,
   "`": 8,