Skip to content

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

fix FunOfflineInfer

雾聪e29e245bcdb7
diff --git a/runtime/onnxruntime/src/funasrruntime.cpp b/runtime/onnxruntime/src/funasrruntime.cpp
index 31f8a955c..3323b1021 100644
--- a/runtime/onnxruntime/src/funasrruntime.cpp
+++ b/runtime/onnxruntime/src/funasrruntime.cpp
@@ -378,7 +378,6 @@
if (wfst_decoder){
wfst_decoder->StartUtterance();
}
- vector<string> msgs = (offline_stream->asr_handle)->Forward(buff, len, true, hw_emb, dec_handle, batch_in);
vector<string> msg_batch = (offline_stream->asr_handle)->Forward(buff, len, true, hw_emb, dec_handle, batch_in);
for(int idx=0; idx<batch_in; idx++){
string msg = msg_batch[idx];