add tokenizer

special_tokens_map.json

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

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": "/workspace/output_models/fa/xlsr-fa/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "m3hrdadfi/wav2vec2-large-xlsr-persian-v3", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -1 +1 @@
-{"ا": 1, "ب": 2, "ت": 3, "ث": 4, "ج": 5, "ح": 6, "خ": 7, "د": 8, "ذ": 9, "ر": 10, "ز": 11, "س": 12, "ش": 13, "ص": 14, "ض": 15, "ط": 16, "ظ": 17, "ع": 18, "غ": 19, "ف": 20, "ق": 21, "ل": 22, "م": 23, "ن": 24, "و": 25, "ٹ": 26, "پ": 27, "چ": 28, "ڈ": 29, "ڑ": 30, "ژ": 31, "ک": 32, "گ": 33, "ھ": 34, "ہ": 35, "ی": 36, "ے": 37, "|": 0, "[UNK]": 38, "[PAD]": 39}
+{"<pad>": 0, "<s>": 1, "</s>": 2, "<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}