Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": null,
+  "do_lower_case": false,
+  "eos_token": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "wav2vec_lm_farsi",
+  "pad_token": "<pad>",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": "/workspace/output_models/fa/xlsr-fa/special_tokens_map.json",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "tokenizer_file": null,
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,40 @@
+{
+  "<pad>": 0,
+  "<unk>": 3,
+  "|": 4,
+  "آ": 5,
+  "ئ": 6,
+  "ا": 7,
+  "ب": 8,
+  "ت": 9,
+  "ث": 10,
+  "ج": 11,
+  "ح": 12,
+  "خ": 13,
+  "د": 14,
+  "ذ": 15,
+  "ر": 16,
+  "ز": 17,
+  "س": 18,
+  "ش": 19,
+  "ص": 20,
+  "ض": 21,
+  "ط": 22,
+  "ظ": 23,
+  "ع": 24,
+  "غ": 25,
+  "ف": 26,
+  "ق": 27,
+  "ل": 28,
+  "م": 29,
+  "ن": 30,
+  "ه": 31,
+  "و": 32,
+  "پ": 33,
+  "چ": 34,
+  "ژ": 35,
+  "ک": 36,
+  "گ": 37,
+  "ی": 38,
+  "‌": 39
+}