Fix peprocessor config
Browse files- added_tokens.json +1 -0
- tokenizer_config.json +1 -1
- vocab.json +1 -1
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<s>": 78, "</s>": 79}
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|"}
|
|
|
1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": "/content/drive/MyDrive/wav2vec2-large-xlsr-spa/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/content/drive/MyDrive/wav2vec2-large-xlsr-spa"}
|
vocab.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"п": 0, "ő": 1, "к": 2, "i": 3, "ä": 4, "ş": 5, "ú": 6, "á": 7, "ð": 8, "r": 9, "š": 10, "z": 11, "е": 12, "ү": 13, "–": 14, "ө": 15, "ê": 16, "¡": 17, "ü": 19, "ã": 20, "n": 21, "ш": 22, "л": 23, "ô": 24, "а": 25, "’": 26, "o": 27, "w": 28, "f": 29, "p": 30, "h": 31, "j": 32, "ó": 33, "т": 34, "¿": 35, "ō": 36, "a": 37, "ö": 38, "ò": 39, "g": 40, "р": 41, "c": 42, "e": 43, "t": 44, "u": 45, "ū": 46, "ʻ": 47, "q": 48, "v": 49, "=": 50, "б": 51, "毵": 52, "l": 53, "н": 54, "ø": 55, "ñ": 56, "—": 57, "°": 58, "â": 59, "ë": 60, "´": 61, "y": 62, "x": 63, "m": 64, "'": 65, "é": 66, "и": 67, "í": 68, "ə": 69, "ы": 70, "b": 71, "о": 72, "k": 73, "s": 74, "d": 75, "|": 18, "[UNK]": 76, "[PAD]": 77}
|