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

RNNLM model support lm_num_thread and lm_provider setting (#173)

Browse Source 
* rnnlm model inference supports num_threads setting

* rnnlm params decouple num_thread and provider with Transducer.

* fix python csrc bug which offline-lm-config.cc and online-lm-config.cc arguments problem

* lm_num_threads and lm_provider set default values

---------

Co-authored-by: cuidongcai1035 <cuidongcai1035@wezhuiyi.com>
This commit is contained in:
keanu
2023-06-12 15:51:27 +08:00
committed by GitHub
parent 13b33fcc08
commit 1a1b9fd236
18 changed files with 67 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
sherpa-onnx/csrc/offline-rnn-lm.cc
View File

@@ -18,12 +18,12 @@ namespace sherpa_onnx {
class OfflineRnnLM::Impl {
public:
explicit Impl(const OfflineRecognizerConfig &config)
: config_(config.lm_config),
explicit Impl(const OfflineLMConfig &config)
: config_(config),
env_(ORT_LOGGING_LEVEL_ERROR),
sess_opts_{GetSessionOptions(config.model_config)},
sess_opts_{GetSessionOptions(config)},
allocator_{} {
Init(config.lm_config);
Init(config);
}
Ort::Value Rescore(Ort::Value x, Ort::Value x_lens) {
@@ -63,7 +63,7 @@ class OfflineRnnLM::Impl {
std::vector<const char *> output_names_ptr_;
};
OfflineRnnLM::OfflineRnnLM(const OfflineRecognizerConfig &config)
OfflineRnnLM::OfflineRnnLM(const OfflineLMConfig &config)
: impl_(std::make_unique<Impl>(config)) {}
OfflineRnnLM::~OfflineRnnLM() = default;