When using CUDA sherpa just crashes without any info about the problem.

[gamersagainstweed]

I have Nvidia GPU with Compute capability 6.1 and CUDA 11.8 installed.

I'm using sherpa-onnx-v1.11.3-win-x64-cuda on Win10 x64.

sherpa-onnx-offline.exe --tokens=./sherpa-onnx-zipformer-en-2023-03-30/tokens.txt --encoder=./sherpa-onnx-zipformer-en-2023-03-30/encoder-epoch-99-avg-1.onnx --decoder=./sherpa-onnx-zipformer-en-2023-03-30/decoder-epoch-99-avg-1.onnx --joiner=./sherpa-onnx-zipformer-en-2023-03-30/joiner-epoch-99-avg-1.onnx --provider="cpu" test.wav

This command have executed successfully and produced the expected results.

Changing the provider to CUDA causes software to crash during config creation without providing any information about the cause:

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="./sherpa-onnx-zipformer-en-2023-03-30/encoder-epoch-99-avg-1.onnx", decoder_filename="./sherpa-onnx-zipformer-en-2023-03-30/decoder-epoch-99-avg-1.onnx", joiner_filename="./sherpa-onnx-zipformer-en-2023-03-30/joiner-epoch-99-avg-1.onnx"), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model=""), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-zipformer-en-2023-03-30/tokens.txt", num_threads=2, debug=False, provider="cuda", 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 ...