Upload tokenizer

README.md

@@ -1,20 +1,20 @@
 ---
-library_name: transformers
-license: cc-by-nc-4.0
 base_model: facebook/mms-1b-all
-tags:
-- generated_from_trainer
 datasets:
 - common_voice_17_0
+library_name: transformers
+license: cc-by-nc-4.0
 metrics:
 - wer
 - bleu
+tags:
+- generated_from_trainer
 model-index:
 - name: wav2vec2-mms-1b-CV17.0-training_set_variations
   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
@@ -22,12 +22,12 @@ model-index:
       split: validation
       args: ta
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 0.4582664894348444
-    - name: Bleu
-      type: bleu
+      name: Wer
+    - type: bleu
       value: 0.3001349308741465
+      name: Bleu
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

tokenizer_config.json

@@ -39,9 +39,8 @@
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "processor_class": "Wav2Vec2Processor",
   "replace_word_delimiter_char": " ",
-  "target_lang": "tam-64",
+  "target_lang": "tam-128",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"