Recording with arecord on a Raspberry Pi 4B 4G and then attempting offline ASR results in an error.

[Tony-xubiao]

logs ：

xubiao@raspxubiao:~/sherpa/onnx/sherpa-onnx $ sudo arecord -D "plughw:2,0" --format S16_LE --rate 16000 xb.wav
Recording WAVE 'xb.wav' : Signed 16 bit Little Endian, Rate 16000 Hz, Mono
^CAborted by signal Interrupt...
arecord: pcm_read:2221: read error: Interrupted system call
xubiao@raspxubiao:~/sherpa/onnx/sherpa-onnx $ ./cross-compiled/bin/sherpa-onnx-offline --tokens=./icefall-asr-zipformer-wenetspeech-20230615/data/lang_char/tokens.txt   --encoder=./icefall-asr-zipformer-wenetspeech-20230615/exp/encoder-epoch-12-avg-4.onnx   --decoder=./icefall-asr-zipformer-wenetspeech-20230615/exp/decoder-epoch-12-avg-4.onnx   --joiner=./icefall-asr-zipformer-wenetspeech-20230615/exp/joiner-epoch-12-avg-4.onnx  ./xb.wav 
/home/tontron/software/gcc-arm-10.3-2021.07-x86_64-arm-none-linux-gnueabihf/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:375 ./cross-compiled/bin/sherpa-onnx-offline --tokens=./icefall-asr-zipformer-wenetspeech-20230615/data/lang_char/tokens.txt --encoder=./icefall-asr-zipformer-wenetspeech-20230615/exp/encoder-epoch-12-avg-4.onnx --decoder=./icefall-asr-zipformer-wenetspeech-20230615/exp/decoder-epoch-12-avg-4.onnx --joiner=./icefall-asr-zipformer-wenetspeech-20230615/exp/joiner-epoch-12-avg-4.onnx ./xb.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="./icefall-asr-zipformer-wenetspeech-20230615/exp/encoder-epoch-12-avg-4.onnx", decoder_filename="./icefall-asr-zipformer-wenetspeech-20230615/exp/decoder-epoch-12-avg-4.onnx", joiner_filename="./icefall-asr-zipformer-wenetspeech-20230615/exp/joiner-epoch-12-avg-4.onnx"), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model=""), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), telespeech_ctc="", tokens="./icefall-asr-zipformer-wenetspeech-20230615/data/lang_char/tokens.txt", num_threads=2, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="")
Creating recognizer ...
Started
terminate called after throwing an instance of 'std::length_error'
  what():  cannot create std::vector larger than max_size()
Aborted
xubiao@raspxubiao:~/sherpa/onnx/sherpa-onnx $ ./cross-compiled/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-paraformer-trilingual-zh-cantonese-en/tokens.txt   --paraformer=./sherpa-onnx-paraformer-trilingual-zh-cantonese-en/model.onnx  ./xb.wav                
/home/tontron/software/gcc-arm-10.3-2021.07-x86_64-arm-none-linux-gnueabihf/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:375 ./cross-compiled/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-paraformer-trilingual-zh-cantonese-en/tokens.txt --paraformer=./sherpa-onnx-paraformer-trilingual-zh-cantonese-en/model.onnx ./xb.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model="./sherpa-onnx-paraformer-trilingual-zh-cantonese-en/model.onnx"), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model=""), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), telespeech_ctc="", tokens="./sherpa-onnx-paraformer-trilingual-zh-cantonese-en/tokens.txt", num_threads=2, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="")
Creating recognizer ...
Started
terminate called after throwing an instance of 'std::length_error'
  what():  cannot create std::vector larger than max_size()
Aborted

[csukuangfj]

Before running sherpa-onnx, please make sure you are able to use arecord to record with your microphone.

[csukuangfj]

what is the output of

soxi xb.wav

?

[csukuangfj]

Are you able to decode the test_wavs/*.wav inside the model directory?