Upload tokenizer

README.md

@@ -1,18 +1,18 @@
 ---
-license: cc-by-nc-4.0
 base_model: utter-project/mHuBERT-147
-tags:
-- generated_from_trainer
 datasets:
 - common_voice_17_0
+license: cc-by-nc-4.0
 metrics:
 - wer
+tags:
+- generated_from_trainer
 model-index:
 - name: training
   results:
   - task:
-      name: Automatic Speech Recognition
       type: automatic-speech-recognition
+      name: Automatic Speech Recognition
     dataset:
       name: common_voice_17_0
       type: common_voice_17_0
@@ -20,9 +20,9 @@ model-index:
       split: test
       args: ba
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 0.12020672995899107
+      name: Wer
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 40,
+  "<s>": 39
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "37": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "40": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,41 @@
+{
+  "[PAD]": 38,
+  "[UNK]": 37,
+  "|": 0,
+  "а": 1,
+  "б": 2,
+  "в": 3,
+  "г": 4,
+  "д": 5,
+  "ж": 6,
+  "з": 7,
+  "и": 8,
+  "й": 9,
+  "к": 10,
+  "л": 11,
+  "м": 12,
+  "н": 13,
+  "о": 14,
+  "п": 15,
+  "р": 16,
+  "с": 17,
+  "т": 18,
+  "у": 19,
+  "ф": 20,
+  "х": 21,
+  "ц": 22,
+  "ч": 23,
+  "ш": 24,
+  "щ": 25,
+  "ы": 26,
+  "э": 27,
+  "ғ": 28,
+  "ҙ": 29,
+  "ҡ": 30,
+  "ң": 31,
+  "ҫ": 32,
+  "ү": 33,
+  "һ": 34,
+  "ә": 35,
+  "ө": 36
+}