Skip to content

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

fix: initialize ggml timer in funasr nano cli (#3210)

Maigic098654e8db63
diff --git a/runtime/llama.cpp/fun-asr-nano/funasr-cli/funasr-cli.cpp b/runtime/llama.cpp/fun-asr-nano/funasr-cli/funasr-cli.cpp
index f9266943b..26f60d52b 100644
--- a/runtime/llama.cpp/fun-asr-nano/funasr-cli/funasr-cli.cpp
+++ b/runtime/llama.cpp/fun-asr-nano/funasr-cli/funasr-cli.cpp
@@ -184,6 +184,7 @@ int main(int argc,char**argv){
std::vector<float> wav;
if(!funasr_load_audio_16k_mono(wav_path.c_str(),wav)){fprintf(stderr,"failed to read audio\n");return 1;}
+ ggml_time_init(); // Required before ggml_time_us() on Windows.
int64_t t0=ggml_time_us();
enc_model em; if(!load_enc(enc_path.c_str(),em))return 1;