Configuration for a streaming ASR recognizer. More...

#include <c-api.h>

Collaboration diagram for SherpaOnnxOnlineRecognizerConfig:

Public Attributes
SherpaOnnxFeatureConfig	feat_config

SherpaOnnxOnlineModelConfig	model_config

const char *	decoding_method

int32_t	max_active_paths

int32_t	enable_endpoint

float	rule1_min_trailing_silence

float	rule2_min_trailing_silence

float	rule3_min_utterance_length

const char *	hotwords_file

float	hotwords_score

SherpaOnnxOnlineCtcFstDecoderConfig	ctc_fst_decoder_config

const char *	rule_fsts

const char *	rule_fars

float	blank_penalty

const char *	hotwords_buf

int32_t	hotwords_buf_size

SherpaOnnxHomophoneReplacerConfig	hr

Detailed Description

Zero-initialize this struct before use. Then fill in feat_config, model_config, and any optional decoding, endpoint, or hotword settings.

Example model package: sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20

SherpaOnnxOnlineRecognizerConfig config;
memset(&config, 0, sizeof(config));
 
config.feat_config.sample_rate = 16000;
config.feat_config.feature_dim = 80;
 
config.model_config.transducer.encoder =
    "./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/"
    "encoder-epoch-99-avg-1.int8.onnx";
config.model_config.transducer.decoder =
    "./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/"
    "decoder-epoch-99-avg-1.onnx";
config.model_config.transducer.joiner =
    "./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/"
    "joiner-epoch-99-avg-1.int8.onnx";
config.model_config.tokens =
    "./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/"
    "tokens.txt";
config.model_config.provider = "cpu";
config.model_config.num_threads = 1;
 
config.decoding_method = "greedy_search";

Definition at line 337 of file c-api.h.

Member Data Documentation

◆ blank_penalty

float SherpaOnnxOnlineRecognizerConfig::blank_penalty

Optional blank penalty applied during decoding.

Definition at line 374 of file c-api.h.

◆ ctc_fst_decoder_config

SherpaOnnxOnlineCtcFstDecoderConfig SherpaOnnxOnlineRecognizerConfig::ctc_fst_decoder_config

Optional HLG/FST online CTC decoder configuration.

Definition at line 368 of file c-api.h.

◆ decoding_method

const char* SherpaOnnxOnlineRecognizerConfig::decoding_method

Decoding method, for example "greedy_search" or "modified_beam_search".

Definition at line 344 of file c-api.h.

◆ enable_endpoint

int32_t SherpaOnnxOnlineRecognizerConfig::enable_endpoint

Set to non-zero to enable endpoint detection.

Definition at line 350 of file c-api.h.

◆ feat_config

SherpaOnnxFeatureConfig SherpaOnnxOnlineRecognizerConfig::feat_config

Feature extraction settings.

Definition at line 339 of file c-api.h.

◆ hotwords_buf

const char* SherpaOnnxOnlineRecognizerConfig::hotwords_buf

Optional in-memory hotwords text used instead of hotwords_file.

Definition at line 377 of file c-api.h.

◆ hotwords_buf_size

int32_t SherpaOnnxOnlineRecognizerConfig::hotwords_buf_size

Size in bytes of hotwords_buf, excluding the trailing '\0'.

Definition at line 379 of file c-api.h.

◆ hotwords_file

const char* SherpaOnnxOnlineRecognizerConfig::hotwords_file

Path to a hotwords file.

Definition at line 362 of file c-api.h.

◆ hotwords_score

float SherpaOnnxOnlineRecognizerConfig::hotwords_score

Bonus score added to each hotword token during decoding.

Definition at line 365 of file c-api.h.

◆ hr

SherpaOnnxHomophoneReplacerConfig SherpaOnnxOnlineRecognizerConfig::hr

Optional homophone replacement configuration.

Definition at line 381 of file c-api.h.

◆ max_active_paths

int32_t SherpaOnnxOnlineRecognizerConfig::max_active_paths

Number of active paths for modified beam search.

Definition at line 347 of file c-api.h.

◆ model_config

SherpaOnnxOnlineModelConfig SherpaOnnxOnlineRecognizerConfig::model_config

Streaming model configuration.

Definition at line 341 of file c-api.h.

◆ rule1_min_trailing_silence

float SherpaOnnxOnlineRecognizerConfig::rule1_min_trailing_silence

Endpoint rule 1 trailing silence threshold in seconds.

Definition at line 353 of file c-api.h.

◆ rule2_min_trailing_silence

float SherpaOnnxOnlineRecognizerConfig::rule2_min_trailing_silence

Endpoint rule 2 trailing silence threshold in seconds.

Definition at line 356 of file c-api.h.

◆ rule3_min_utterance_length

float SherpaOnnxOnlineRecognizerConfig::rule3_min_utterance_length

Endpoint rule 3 utterance-length threshold in seconds.

Definition at line 359 of file c-api.h.

◆ rule_fars

const char* SherpaOnnxOnlineRecognizerConfig::rule_fars

Path to FAR archives used by text-processing rules.

Definition at line 372 of file c-api.h.

◆ rule_fsts

const char* SherpaOnnxOnlineRecognizerConfig::rule_fsts

Path to punctuation or text-processing rule FSTs.

Definition at line 370 of file c-api.h.

The documentation for this struct was generated from the following file:

c-api/c-api.h

Public Attributes