stepfun-ai
/

Step-Audio-Tokenizer

Model card Files Files and versions Community

Step-Audio-Tokenizer / dengcunqin /speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online

Ctrl+K

Ctrl+K

2 contributors

History: 1 commit

buyun's picture

initial

e70375e verified 5 months ago

example
initial 5 months ago
.mdl

102 Bytes

initial 5 months ago
.msc

869 Bytes

initial 5 months ago
.mv
36 Bytes

initial 5 months ago
README.md
4.74 kB

initial 5 months ago
am.mvn

11.2 kB

initial 5 months ago
config.yaml

2.94 kB

initial 5 months ago
configuration.json

482 Bytes

initial 5 months ago
model.pt

881 MB
LFS

initial 5 months ago
seg_dict

8.29 MB

initial 5 months ago
tokens.json

99.5 kB

initial 5 months ago
tokens.txt

39.9 kB

initial 5 months ago
write_tokens_from_txt.py

389 Bytes

initial 5 months ago