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
add log for torch
雾聪6a8c595fc3ca
diff --git a/runtime/onnxruntime/src/paraformer-torch.cpp b/runtime/onnxruntime/src/paraformer-torch.cppindex bdfd0eeb0..7cac2918a 100644--- a/runtime/onnxruntime/src/paraformer-torch.cpp+++ b/runtime/onnxruntime/src/paraformer-torch.cpp@@ -45,8 +45,15 @@ void ParaformerTorch::InitAsr(const std::string &am_model, const std::string &am#ifdef USE_IPEXtorch::jit::setTensorExprFuserEnabled(false);#endif- torch::jit::script::Module model = torch::jit::load(am_model, device);- model_ = std::make_shared<TorchModule>(std::move(model));++ try {+ torch::jit::script::Module model = torch::jit::load(am_model, device);+ model_ = std::make_shared<TorchModule>(std::move(model));+ LOG(INFO) << "Successfully load model from " << am_model;+ } catch (std::exception const &e) {+ LOG(ERROR) << "Error when load am model: " << e.what();+ exit(-1);+ }}void ParaformerTorch::InitLm(const std::string &lm_file,