public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-17 20:03:45 +02:00
Code Issues Packages Projects Releases Wiki Activity

server: add support for carry_initial_prompt (#3781)

Browse Source 
* Add support for carry_initial_prompt on the server

* Update README
This commit is contained in:
Andreas Lubbe
2026-05-15 14:03:17 +02:00
committed by GitHub
parent 46ca43d639
commit 968eebe772
2 changed files with 146 additions and 142 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/server/README.md
+3
View File
@@ -40,6 +40,7 @@ options:
-l LANG, --language LANG [en ] spoken language ('auto' for auto-detect)
-dl, --detect-language [false ] exit after automatically detecting language
--prompt PROMPT [ ] initial prompt
--carry-initial-prompt [false ] always prepend initial prompt
-m FNAME, --model FNAME [models/ggml-base.en.bin] model path
-oved D, --ov-e-device DNAME [CPU ] the OpenVINO device used for encode inference
-dtw MODEL --dtw MODEL [ ] compute token-level timestamps
@@ -78,6 +79,8 @@ curl 127.0.0.1:8080/inference \
-F file="@<file-path>" \
-F temperature="0.0" \
-F temperature_inc="0.2" \
-F prompt="<prompt>" \
-F carry_initial_prompt="true" \
-F response_format="json"
```