Update README.md

diff --git a/examples/stream/README.md b/examples/stream/README.md
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..8b4c8a6a4b92cbed4d702b586d8012feb6ff5bf4 100644 (file)
--- a/examples/stream/README.md
+++ b/examples/stream/README.md
@@ -0,0 +1,23 @@
+# stream\r
+\r
+This is a naive example of performing real-time inference on audio from your microphone.\r
+The `stream` tool samples the audio every half a second and runs the transcription continously.\r
+More info is available in [issue #10](https://github.com/ggerganov/whisper.cpp/issues/10).\r
+\r
+```java\r
+./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
+\r
+The `stream` tool depends on SDL2 library to capture audio from the microphone. You can build it like this:\r
+\r
+```bash\r
+# Install SDL2 on Linux\r
+sudo apt-get install libsdl2-dev\r
+\r
+# Install SDL2 on Mac OS\r
+brew install sdl2\r
+\r
+make stream\r
+```\r