Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
DiscreteSpeech
/
DSTK
like
7
Follow
Discrete Speech Project
6
English
Chinese
speech
tokenization
detokenization
text2token
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
DSTK
/
semantic_tokenizer
/
f40ms
3.87 GB
1 contributor
History:
4 commits
gooorillax
refine readme, add logo, and fix a punct normalization problem in tn
bdecca1
about 2 months ago
ckpt
first push of codes and models for g2p, t2u, tokenizer and detokenizer
2 months ago
config
first push of codes and models for g2p, t2u, tokenizer and detokenizer
2 months ago
models
first push of codes and models for g2p, t2u, tokenizer and detokenizer
2 months ago
modules
first push of codes and models for g2p, t2u, tokenizer and detokenizer
2 months ago
README.md
1.11 kB
refine readme, add logo, and fix a punct normalization problem in tn
about 2 months ago
__init__.py
Safe
0 Bytes
first push of codes and models for g2p, t2u, tokenizer and detokenizer
2 months ago
fairseq_npu_patch.py
Safe
1.18 kB
first push of codes and models for g2p, t2u, tokenizer and detokenizer
2 months ago
infer_for_eval.py
Safe
5.09 kB
first push of codes and models for g2p, t2u, tokenizer and detokenizer
2 months ago
patch_utils.py
Safe
4.88 kB
first push of codes and models for g2p, t2u, tokenizer and detokenizer
2 months ago
requirements_npu.txt
Safe
98 Bytes
first push of codes and models for g2p, t2u, tokenizer and detokenizer
2 months ago
simple_tokenizer_infer.py
Safe
10.3 kB
first push of codes and models for g2p, t2u, tokenizer and detokenizer
2 months ago