add vcpkg.json

Author: litongjava

CMakeLists.txt

@@ -3,27 +3,14 @@ project(whisper_cpp_server)
 
 set(CMAKE_CXX_STANDARD 14)
 # find SDL2 library
-find_package(SDL2 REQUIRED)
+find_package(SDL2 CONFIG REQUIRED)
 include_directories(${SDL2_INCLUDE_DIRS})
 
-
-# 检测操作系统
-if (${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
-    # macOS
-    include_directories(/Users/ping/code/cpp/project-litongjava/whisper.cpp)
-    link_directories(/Users/ping/code/cpp/project-litongjava/whisper.cpp/cmake-build-release)
-elseif (${CMAKE_SYSTEM_NAME} MATCHES "Linux")
-    # Linux
-    include_directories(/mnt/e/code/cpp/project-ping/whisper.cpp)
-    link_directories(/mnt/e/code/cpp/project-ping/whisper.cpp/cmake-build-release)
-endif ()
-
-add_executable(web_socket_server main.cpp web_socket_server.cpp)
-# 链接 whisper.cpp 库
-target_link_libraries(web_socket_server whisper ${SDL2_LIBRARIES})
-
+add_executable(sdl_version sdl_version.cpp)
+target_link_libraries(sdl_version ${SDL2_LIBRARIES})
 add_executable(stream_components stream_components.cpp)
 target_link_libraries(stream_components whisper ${SDL2_LIBRARIES})
 
-
+#add_executable(server server.cpp httplib.h json.hpp)
+#target_link_libraries(server common.cpp whisper)
 

README.md

@@ -0,0 +1,59 @@
+# whisper-cpp server
+
+Simple http server. WAV Files are passed to the inference model via http requests.
+
+```
+./server -h
+
+usage: ./bin/server [options]
+
+options:
+  -h,        --help              [default] show this help message and exit
+  -t N,      --threads N         [4      ] number of threads to use during computation
+  -p N,      --processors N      [1      ] number of processors to use during computation
+  -ot N,     --offset-t N        [0      ] time offset in milliseconds
+  -on N,     --offset-n N        [0      ] segment index offset
+  -d  N,     --duration N        [0      ] duration of audio to process in milliseconds
+  -mc N,     --max-context N     [-1     ] maximum number of text context tokens to store
+  -ml N,     --max-len N         [0      ] maximum segment length in characters
+  -sow,      --split-on-word     [false  ] split on word rather than on token
+  -bo N,     --best-of N         [2      ] number of best candidates to keep
+  -bs N,     --beam-size N       [-1     ] beam size for beam search
+  -wt N,     --word-thold N      [0.01   ] word timestamp probability threshold
+  -et N,     --entropy-thold N   [2.40   ] entropy threshold for decoder fail
+  -lpt N,    --logprob-thold N   [-1.00  ] log probability threshold for decoder fail
+  -debug,    --debug-mode        [false  ] enable debug mode (eg. dump log_mel)
+  -tr,       --translate         [false  ] translate from source language to english
+  -di,       --diarize           [false  ] stereo audio diarization
+  -tdrz,     --tinydiarize       [false  ] enable tinydiarize (requires a tdrz model)
+  -nf,       --no-fallback       [false  ] do not use temperature fallback while decoding
+  -ps,       --print-special     [false  ] print special tokens
+  -pc,       --print-colors      [false  ] print colors
+  -pp,       --print-progress    [false  ] print progress
+  -nt,       --no-timestamps     [false  ] do not print timestamps
+  -l LANG,   --language LANG     [en     ] spoken language ('auto' for auto-detect)
+  -dl,       --detect-language   [false  ] exit after automatically detecting language
+             --prompt PROMPT     [       ] 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
+  --host HOST,                   [127.0.0.1] Hostname/ip-adress for the server
+  --port PORT,                   [8080   ] Port number for the server
+```
+
+## request examples
+
+**/inference**
+```
+curl 127.0.0.1:8080/inference \
+-H "Content-Type: multipart/form-data" \
+-F file="<file-path>" \
+-F temperature="0.2" \
+-F response-format="json"
+```
+
+**/load**
+```
+curl 127.0.0.1:8080/load \
+-H "Content-Type: multipart/form-data" \
+-F model="<path-to-model-file>"
+```