Skip to content

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

update warmup to 10

雾聪16a3cd3cfb86
diff --git a/runtime/onnxruntime/bin/funasr-onnx-offline-rtf.cpp b/runtime/onnxruntime/bin/funasr-onnx-offline-rtf.cpp
index c2a68fc7b..8afa77a05 100644
--- a/runtime/onnxruntime/bin/funasr-onnx-offline-rtf.cpp
+++ b/runtime/onnxruntime/bin/funasr-onnx-offline-rtf.cpp
@@ -52,7 +52,7 @@ void runReg(FUNASR_HANDLE asr_handle, vector<string> wav_list, vector<string> wa
std::vector<std::vector<float>> hotwords_embedding = CompileHotwordEmbedding(asr_handle, nn_hotwords_);
// warm up
- for (size_t i = 0; i < 1; i++)
+ for (size_t i = 0; i < 10; i++)
{
FUNASR_RESULT result=FunOfflineInfer(asr_handle, wav_list[0].c_str(), RASR_NONE, nullptr, hotwords_embedding, audio_fs, true, decoder_handle);
if(result){