Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

docs: build note — copy funasr-common alongside the example (shared miniaudio audio loader) (#2996)

zhifu gao4a93f293336c
diff --git a/runtime/llama.cpp/README.md b/runtime/llama.cpp/README.md
index 5b7d7b56a..ca8645cd8 100644
--- a/runtime/llama.cpp/README.md
+++ b/runtime/llama.cpp/README.md
@@ -42,6 +42,7 @@ cmake --build build -j # -> build/bin/llama-funasr-* (a
## Build (shared)
```bash
git clone https://github.com/ggml-org/llama.cpp && cd llama.cpp
+cp -r /path/to/runtime/llama.cpp/funasr-common examples/ # shared audio loader (miniaudio); each example CMake adds ../funasr-common
cp -r /path/to/runtime/llama.cpp/<model>/<example-dir> examples/
echo 'add_subdirectory(<example-dir>)' >> examples/CMakeLists.txt
cmake -B build -DGGML_NATIVE=ON -DLLAMA_CURL=OFF