Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
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.cppindex 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;