 spicysama
|
4ae0d0734c
Fix infer warmup (#530)
|
1 年之前 |
|
spicysama
|
9cb84a6da5
Update docs etc. (#524)
|
1 年之前 |
 Lengyue
|
1e7a2b0a16
update webui
|
1 年之前 |
|
Lengyue
|
dad516d86d
update checkpoint path
|
1 年之前 |
|
spicysama
|
237f4fdcb9
fully support ormsgpack (#518)
|
1 年之前 |
|
spicysama
|
e9394c71f0
keep up with official close-source api (#513)
|
1 年之前 |
|
spicysama
|
8702c61100
From whisper to sensevoice (#482)
|
1 年之前 |
 Ftps
|
cc7afe8d7b
Support inference on mps device natively (#461)
|
1 年之前 |
 PoTaTo
|
dc250abf67
add auto_rerank part (#393)
|
1 年之前 |
|
Lengyue
|
1d942c8b97
Update 1.2 sft checkpoints, inference.ipynb and READMEs
|
1 年之前 |
|
spicysama
|
5dd593fef3
Add Quick Start (#363)
|
1 年之前 |
|
spicysama
|
61b6609981
Fix api (#321)
|
1 年之前 |
|
Lengyue
|
c7d9e3fcaa
fix webui & api for fs 1.2
|
1 年之前 |
|
spicysama
|
584be1d047
Adaptation to version 1.2 (#301)
|
1 年之前 |
|
Leng Yue
|
5e7914472f
This PR brings V1.2 inference into main (#300)
|
1 年之前 |
|
Lengyue
|
46dae9bd1c
Replace zibai with uvicorn
|
1 年之前 |
 spicysama
|
1e83d31959
API support: ref audio (#241)
|
1 年之前 |
|
spicysama
|
70de7876f6
优化模型/配置文件选择时的体验 (#228)
|
1 年之前 |
|
Lengyue
|
dbd3b18bf2
[Breaking] Add new text-splitter, new length based on bytes
|
1 年之前 |
|
Lengyue
|
dd1687a9d0
rm unused code
|
1 年之前 |
|
Lengyue
|
50447798f8
Optimize long-audio cache & support vits decoder
|
1 年之前 |
|
Lengyue
|
9a18199a3e
Return error for empty input
|
1 年之前 |
|
Lengyue
|
9677932a21
Fix document (use medium by default)
|
1 年之前 |
|
Lengyue
|
58cdfd7b5c
Remove silence padding (it make sounds unnatural)
|
1 年之前 |
|
Lengyue
|
e787d0182f
Use SFT medium as base model
|
1 年之前 |
|
Lengyue
|
231b8ed6ad
Enable API stream generation & reduce WebUI GPU memory usage
|
1 年之前 |
|
Lengyue
|
813868fc87
Optimize compute graph for dynamic params
|
1 年之前 |
|
Lengyue
|
dbfb1f34d3
Optimize launching directly instead of module
|
1 年之前 |
|
Lengyue
|
dcbe986fc9
Add queue to support streaming
|
1 年之前 |
|
Lengyue
|
6e88efb5d8
update deps & remove audios
|
1 年之前 |
