EngineX-Iluvatar/enginex-mr_series-sherpa-onnx
Archived
16
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Reduce model initialization time for online speech recognition (#215)

Browse Source 
* Reduce model initialization time for online speech recognition

* Fixed Styling

---------

Co-authored-by: w11wo <wilsowong961@gmail.com>
This commit is contained in:
Wilson Wongso
2023-07-14 20:20:10 +07:00
committed by GitHub
parent fe0630fe1f
commit 5a6b55c5a7
7 changed files with 69 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
sherpa-onnx/c-api/c-api.cc
View File

@@ -50,6 +50,8 @@ SherpaOnnxOnlineRecognizer *CreateOnlineRecognizer(
SHERPA_ONNX_OR(config->model_config.num_threads, 1);
recognizer_config.model_config.provider =
SHERPA_ONNX_OR(config->model_config.provider, "cpu");
recognizer_config.model_config.model_type =
SHERPA_ONNX_OR(config->model_config.model_type, "");
recognizer_config.model_config.debug =
SHERPA_ONNX_OR(config->model_config.debug, 0);

1
sherpa-onnx/c-api/c-api.h
View File

@@ -53,6 +53,7 @@ SHERPA_ONNX_API typedef struct SherpaOnnxOnlineTransducerModelConfig {
const char *tokens;
int32_t num_threads;
const char *provider;
const char *model_type;
int32_t debug; // true to print debug information of the model
} SherpaOnnxOnlineTransducerModelConfig;