Hugging Face's logo

AXERA-TECH
/
CosyVoice3

Text-to-Speech
Transformers
ONNX
English
Chinese
CosyVoice3
Speech
Model card Files
xet
 Community
lihongjie commited on
Commit
6ca7c7e
·
1 Parent(s): ca08716

update

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -35,8 +35,8 @@ For those who are interested in model conversion, you can try to export axmodel
35
  | Stage | Time |
36
  |------|------|
37
  | llm prefill ( input_token_num + prompt_token_num 在 [0,128 ] ) | 104 ms |
38
- | llm prefill ( input_token_num + prompt_token_num 在 [128,256 ] ) | 234 ms |
39
- | Decode | 21.24 token/s |
40
 
41
  ## How to use
42
 
 
35
  | Stage | Time |
36
  |------|------|
37
  | llm prefill ( input_token_num + prompt_token_num 在 [0,128 ] ) | 104 ms |
38
+ | llm prefill ( input_token_num + prompt_token_num 在 [128,256 ] ) | 160 ms |
39
+ | Decode | 14 token/s |
40
 
41
  ## How to use
42