upstream-archive/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-07-23 11:10:57 -05:00
Code Issues Packages Projects Releases Wiki Activity

whisper : rename binaries + fix install (#2648)

Browse Source 
* whisper : rename binaries + fix install

* cont : try to fix ci

* cont : fix emscripten builds
This commit is contained in:
Georgi Gerganov
2024-12-21 09:43:49 +02:00
committed by GitHub
parent e4e05981d6
commit 2e59dced12
44 changed files with 172 additions and 3935 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
examples/command/CMakeLists.txt
View File

@@ -1,9 +1,10 @@
if (WHISPER_SDL2)
# command
set(TARGET command)
set(TARGET whisper-command)
add_executable(${TARGET} command.cpp)
include(DefaultTargetOptions)
target_link_libraries(${TARGET} PRIVATE common common-sdl whisper ${CMAKE_THREAD_LIBS_INIT})
install(TARGETS ${TARGET} RUNTIME)
endif ()

15
examples/command/README.md
View File

@@ -1,14 +1,14 @@
# command
# whisper.cpp/examples/command
This is a basic Voice Assistant example that accepts voice commands from the microphone.
More info is available in [issue #171](https://github.com/ggerganov/whisper.cpp/issues/171).
```bash
# Run with default arguments and small model
./command -m ./models/ggml-small.en.bin -t 8
./whisper-command -m ./models/ggml-small.en.bin -t 8
# On Raspberry Pi, use tiny or base models + "-ac 768" for better performance
./command -m ./models/ggml-tiny.en.bin -ac 768 -t 3 -c 0
./whisper-command -m ./models/ggml-tiny.en.bin -ac 768 -t 3 -c 0
```
https://user-images.githubusercontent.com/1991296/204038393-2f846eae-c255-4099-a76d-5735c25c49da.mp4
@@ -23,10 +23,10 @@ Initial tests show that this approach might be extremely efficient in terms of p
```bash
# Run in guided mode, the list of allowed commands is in commands.txt
./command -m ./models/ggml-base.en.bin -cmd ./examples/command/commands.txt
./whisper-command -m ./models/ggml-base.en.bin -cmd ./examples/command/commands.txt
# On Raspberry Pi, in guided mode you can use "-ac 128" for extra performance
./command -m ./models/ggml-tiny.en.bin -cmd ./examples/command/commands.txt -ac 128 -t 3 -c 0
./whisper-command -m ./models/ggml-tiny.en.bin -cmd ./examples/command/commands.txt -ac 128 -t 3 -c 0
```
https://user-images.githubusercontent.com/1991296/207435352-8fc4ed3f-bde5-4555-9b8b-aeeb76bee969.mp4
@@ -34,7 +34,7 @@ https://user-images.githubusercontent.com/1991296/207435352-8fc4ed3f-bde5-4555-9
## Building
The `command` tool depends on SDL2 library to capture audio from the microphone. You can build it like this:
The `whisper-command` tool depends on SDL2 library to capture audio from the microphone. You can build it like this:
```bash
# Install SDL2
@@ -47,5 +47,6 @@ sudo dnf install SDL2 SDL2-devel
# Install SDL2 on Mac OS
brew install sdl2
make command
cmake -B build -DWHISPER_SDL2=ON
cmake --build build --config Release
```