More info is available in [issue #10](https://github.com/ggerganov/whisper.cpp/issues/10).\r
\r
```bash\r
-./stream -m ./models/ggml-base.en.bin -t 8 --step 500 --length 5000\r
+./build/bin/stream -m ./models/ggml-base.en.bin -t 8 --step 500 --length 5000\r
```\r
\r
https://user-images.githubusercontent.com/1991296/194935793-76afede7-cfa8-48d8-a80f-28ba83be7d09.mp4\r
Setting the `--step` argument to `0` enables the sliding window mode:\r
\r
```bash\r
- ./stream -m ./models/ggml-small.en.bin -t 6 --step 0 --length 30000 -vth 0.6\r
+ ./build/bin/stream -m ./models/ggml-small.en.bin -t 6 --step 0 --length 30000 -vth 0.6\r
```\r
\r
In this mode, the tool will transcribe only after some speech activity is detected. A very\r
# Install SDL2 on Mac OS\r
brew install sdl2\r
\r
-make stream\r
-```\r
-\r
-Ensure you are at the root of the repo when running `make stream`. Not within the `examples/stream` dir\r
-as the libraries needed like `common-sdl.h` are located within `examples`. Attempting to compile within\r
-`examples/steam` means your compiler cannot find them and it gives an error it cannot find the file.\r
+cmake -B build -DWHISPER_SDL2=ON\r
+cmake --build build --config Release\r
\r
-```bash\r
-whisper.cpp/examples/stream$ make stream\r
-g++ stream.cpp -o stream\r
-stream.cpp:6:10: fatal error: common/sdl.h: No such file or directory\r
- 6 | #include "common/sdl.h"\r
- | ^~~~~~~~~~~~~~\r
-compilation terminated.\r
-make: *** [<builtin>: stream] Error 1\r
+./build/bin/stream\r
```\r
\r
## Web version\r