emon1521 commited on
Commit
97199f3
·
1 Parent(s): ffc5097

add tokenizer

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
runs/Apr06_09-40-02_DESKTOP-5GECLH7/1649216496.1858008/events.out.tfevents.1649216496.DESKTOP-5GECLH7.16444.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8525870ecf6eebb7d8eaf6897ebbb3cb8d4b1901015b8ed481f095eedca438eb
3
+ size 4507
runs/Apr06_09-40-02_DESKTOP-5GECLH7/events.out.tfevents.1649216496.DESKTOP-5GECLH7.16444.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e2e60959252ef85412161969f813574079c979e8302b3fba9ab0452ffd5c40d
3
+ size 4463
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"r": 0, "n": 1, "m": 2, "d": 3, "c": 4, "u": 5, "t": 6, "e": 7, "'": 8, "h": 9, "i": 10, "k": 11, "p": 12, "o": 13, "q": 14, "w": 15, "a": 16, "x": 18, "v": 19, "l": 20, "g": 21, "s": 22, "z": 23, "y": 24, "f": 25, "b": 26, "j": 27, "|": 17, "[UNK]": 28, "[PAD]": 29}