游雁
2024-06-09 b75d1e89bb2f513a79bb07e9100ba1cd2bbcf40c
runtime/onnxruntime/src/offline-stream.cpp
@@ -1,7 +1,7 @@
#include "precomp.h"
namespace funasr {
OfflineStream::OfflineStream(std::map<std::string, std::string>& model_path, int thread_num)
OfflineStream::OfflineStream(std::map<std::string, std::string>& model_path, int thread_num, bool use_gpu, int batch_size)
{
    // VAD model
    if(model_path.find(VAD_DIR) != model_path.end()){
@@ -32,10 +32,23 @@
        string am_model_path;
        string am_cmvn_path;
        string am_config_path;
        string token_path;
        string hw_compile_model_path;
        string seg_dict_path;
    
        asr_handle = make_unique<Paraformer>();
        if(use_gpu){
            #ifdef USE_GPU
            asr_handle = make_unique<ParaformerTorch>();
            asr_handle->SetBatchSize(batch_size);
            #else
            LOG(ERROR) <<"GPU is not supported! CPU will be used! If you want to use GPU, please add -DGPU=ON when cmake";
            asr_handle = make_unique<Paraformer>();
            use_gpu = false;
            #endif
        }else{
            asr_handle = make_unique<Paraformer>();
        }
        bool enable_hotword = false;
        hw_compile_model_path = PathAppend(model_path.at(MODEL_DIR), MODEL_EB_NAME);
        seg_dict_path = PathAppend(model_path.at(MODEL_DIR), MODEL_SEG_DICT);
@@ -54,11 +67,21 @@
          if(model_path.find(QUANTIZE) != model_path.end() && model_path.at(QUANTIZE) == "true"){
            am_model_path = PathAppend(model_path.at(MODEL_DIR), QUANT_MODEL_NAME);
          }
          if(use_gpu){
            am_model_path = PathAppend(model_path.at(MODEL_DIR), TORCH_MODEL_NAME);
            if(model_path.find(QUANTIZE) != model_path.end() && model_path.at(QUANTIZE) == "true"){
                am_model_path = PathAppend(model_path.at(MODEL_DIR), TORCH_QUANT_MODEL_NAME);
            }
            if(model_path.find(BLADEDISC) != model_path.end() && model_path.at(BLADEDISC) == "true"){
                am_model_path = PathAppend(model_path.at(MODEL_DIR), BLADE_MODEL_NAME);
            }
          }
        }
        am_cmvn_path = PathAppend(model_path.at(MODEL_DIR), AM_CMVN_NAME);
        am_config_path = PathAppend(model_path.at(MODEL_DIR), AM_CONFIG_NAME);
        token_path = PathAppend(model_path.at(MODEL_DIR), TOKEN_PATH);
        asr_handle->InitAsr(am_model_path, am_cmvn_path, am_config_path, thread_num);
        asr_handle->InitAsr(am_model_path, am_cmvn_path, am_config_path, token_path, thread_num);
    }
    // Lm resource
@@ -79,20 +102,23 @@
    if(model_path.find(PUNC_DIR) != model_path.end()){
        string punc_model_path;
        string punc_config_path;
        string token_path;
    
        punc_model_path = PathAppend(model_path.at(PUNC_DIR), MODEL_NAME);
        if(model_path.find(PUNC_QUANT) != model_path.end() && model_path.at(PUNC_QUANT) == "true"){
            punc_model_path = PathAppend(model_path.at(PUNC_DIR), QUANT_MODEL_NAME);
        }
        punc_config_path = PathAppend(model_path.at(PUNC_DIR), PUNC_CONFIG_NAME);
        token_path = PathAppend(model_path.at(PUNC_DIR), TOKEN_PATH);
        if (access(punc_model_path.c_str(), F_OK) != 0 ||
            access(punc_config_path.c_str(), F_OK) != 0 )
            access(punc_config_path.c_str(), F_OK) != 0 ||
            access(token_path.c_str(), F_OK) != 0)
        {
            LOG(INFO) << "PUNC model file is not exist, skip load punc model.";
        }else{
            punc_handle = make_unique<CTTransformer>();
            punc_handle->InitPunc(punc_model_path, punc_config_path, thread_num);
            punc_handle->InitPunc(punc_model_path, punc_config_path, token_path, thread_num);
            use_punc = true;
        }
    }
@@ -115,10 +141,10 @@
#endif
}
OfflineStream *CreateOfflineStream(std::map<std::string, std::string>& model_path, int thread_num)
OfflineStream *CreateOfflineStream(std::map<std::string, std::string>& model_path, int thread_num, bool use_gpu, int batch_size)
{
    OfflineStream *mm;
    mm = new OfflineStream(model_path, thread_num);
    mm = new OfflineStream(model_path, thread_num, use_gpu, batch_size);
    return mm;
}