@@ -5,7 +5,7 @@ The `stream` tool samples the audio every half a second and runs the transcripti
55More info is available in [ issue #10 ] ( https://github.com/ggerganov/whisper.cpp/issues/10 ) .
66
77``` bash
8- ./stream -m ./models/ggml-base.en.bin -t 8 --step 500 --length 5000
8+ ./build/bin/ stream -m ./models/ggml-base.en.bin -t 8 --step 500 --length 5000
99```
1010
1111https://user-images.githubusercontent.com/1991296/194935793-76afede7-cfa8-48d8-a80f-28ba83be7d09.mp4
@@ -15,7 +15,7 @@ https://user-images.githubusercontent.com/1991296/194935793-76afede7-cfa8-48d8-a
1515Setting the ` --step ` argument to ` 0 ` enables the sliding window mode:
1616
1717``` bash
18- ./stream -m ./models/ggml-small.en.bin -t 6 --step 0 --length 30000 -vth 0.6
18+ ./build/bin/ stream -m ./models/ggml-small.en.bin -t 6 --step 0 --length 30000 -vth 0.6
1919```
2020
2121In this mode, the tool will transcribe only after some speech activity is detected. A very
@@ -40,21 +40,10 @@ sudo dnf install SDL2 SDL2-devel
4040# Install SDL2 on Mac OS
4141brew install sdl2
4242
43- make stream
44- ```
45-
46- Ensure you are at the root of the repo when running ` make stream ` . Not within the ` examples/stream ` dir
47- as the libraries needed like ` common-sdl.h ` are located within ` examples ` . Attempting to compile within
48- ` examples/steam ` means your compiler cannot find them and it gives an error it cannot find the file.
43+ cmake -B build -DWHISPER_SDL2=ON
44+ cmake --build build --config Release
4945
50- ``` bash
51- whisper.cpp/examples/stream$ make stream
52- g++ stream.cpp -o stream
53- stream.cpp:6:10: fatal error: common/sdl.h: No such file or directory
54- 6 | # include "common/sdl.h"
55- | ^~~~~~~~~~~~~~
56- compilation terminated.
57- make: *** [< builtin> : stream] Error 1
46+ ./build/bin/stream
5847```
5948
6049## Web version
0 commit comments