add tokenizer
Browse files- added_tokens.json +1 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<s>": 33, "</s>": 34}
|
special_tokens_map.json
ADDED
@@ -0,0 +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}]}
|
tokenizer_config.json
ADDED
@@ -0,0 +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": "/home/walnabki/eng_asr/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/home/walnabki/eng_asr/", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"[PAD]": 0, "[UNK]": 1, "s": 2, "p": 3, "j": 4, "n": 5, "z": 6, "f": 7, "h": 8, "k": 9, "m": 10, "v": 11, "y": 12, "g": 13, "u": 14, "r": 15, "x": 16, "o": 17, "b": 18, "e": 20, "'": 21, "l": 22, "i": 23, "a": 24, "w": 25, "t": 26, "q": 27, "ç": 28, "-": 29, "ñ": 30, "d": 31, "c": 32, "|": 19}
|