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

Support adding punctuations to the speech recogntion result (#761)

Browse Source
This commit is contained in:
Fangjun Kuang
2024-04-13 12:15:57 +08:00
committed by GitHub
parent 0f4705f775
commit 329fe1aa8b
27 changed files with 867 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
sherpa-onnx/csrc/offline-ct-transformer-model-meta-data.h Normal file
View File

@@ -0,0 +1,29 @@
// sherpa-onnx/csrc/offline-ct-transformer-model-meta_data.h
//
// Copyright (c) 2024 Xiaomi Corporation
#ifndef SHERPA_ONNX_CSRC_OFFLINE_CT_TRANSFORMER_MODEL_META_DATA_H_
#define SHERPA_ONNX_CSRC_OFFLINE_CT_TRANSFORMER_MODEL_META_DATA_H_
#include <string>
#include <unordered_map>
#include <vector>
namespace sherpa_onnx {
struct OfflineCtTransformerModelMetaData {
std::unordered_map<std::string, int32_t> token2id;
std::unordered_map<std::string, int32_t> punct2id;
std::vector<std::string> id2punct;
int32_t unk_id;
int32_t dot_id;
int32_t comma_id;
int32_t quest_id;
int32_t pause_id;
int32_t underline_id;
int32_t num_punctuations;
};
} // namespace sherpa_onnx
#endif // SHERPA_ONNX_CSRC_OFFLINE_CT_TRANSFORMER_MODEL_META_DATA_H_