From b75d1e89bb2f513a79bb07e9100ba1cd2bbcf40c Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期日, 09 六月 2024 00:32:57 +0800
Subject: [PATCH] fix bug

---
 runtime/onnxruntime/src/offline-stream.cpp |   40 +++++++++++++++++++++++++++++++++-------
 1 files changed, 33 insertions(+), 7 deletions(-)

diff --git a/runtime/onnxruntime/src/offline-stream.cpp b/runtime/onnxruntime/src/offline-stream.cpp
index ae8cf18..35eb1ba 100644
--- a/runtime/onnxruntime/src/offline-stream.cpp
+++ b/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;
 }
 

--
Gitblit v1.9.1