Upload tokenizer

README.md

@@ -1,10 +1,10 @@
 ---
-license: apache-2.0
 base_model: facebook/wav2vec2-base
-tags:
-- generated_from_trainer
+license: apache-2.0
 metrics:
 - wer
+tags:
+- generated_from_trainer
 model-index:
 - name: 240615-wav2vec2-ASR-Chinese
   results: []

special_tokens_map.json

@@ -1,30 +1,6 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
-    "single_word": false
-  }
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -39,7 +39,6 @@
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "processor_class": "Wav2Vec2Processor",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json

@@ -1,28 +1,28 @@
 {
   "[PAD]": 25,
   "[UNK]": 24,
-  "a": 5,
-  "b": 14,
-  "c": 16,
-  "d": 3,
-  "e": 4,
-  "f": 20,
-  "g": 0,
-  "h": 19,
-  "i": 15,
-  "k": 21,
-  "l": 18,
-  "m": 22,
-  "n": 12,
-  "o": 13,
-  "p": 1,
-  "r": 23,
-  "s": 7,
-  "t": 11,
-  "u": 17,
-  "v": 6,
-  "w": 8,
-  "x": 9,
-  "y": 10,
-  "|": 2
+  "a": 18,
+  "b": 4,
+  "c": 23,
+  "d": 13,
+  "e": 12,
+  "f": 9,
+  "g": 17,
+  "h": 16,
+  "i": 6,
+  "k": 5,
+  "l": 15,
+  "m": 10,
+  "n": 2,
+  "o": 7,
+  "p": 14,
+  "r": 3,
+  "s": 8,
+  "t": 22,
+  "u": 0,
+  "v": 21,
+  "w": 11,
+  "x": 1,
+  "y": 19,
+  "|": 20
 }