我在识别个别的语音的时候 会有报错

[gwc195795590]

Traceback (most recent call last): File "/Users/guowenchao/Job/AI/FireRedTeadASR/FireRedASR/examples/fireredasr/speech2text.py", line 105, in main(args) File "/Users/guowenchao/Job/AI/FireRedTeadASR/FireRedASR/examples/fireredasr/speech2text.py", line 54, in main results = model.transcribe( File "/opt/homebrew/Caskroom/miniconda/base/envs/fireredasr/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context return func(*args, **kwargs) File "/Users/guowenchao/Job/AI/FireRedTeadASR/FireRedASR/examples/fireredasr/models/fireredasr.py", line 87, in transcribe generated_ids = self.model.transcribe( File "/Users/guowenchao/Job/AI/FireRedTeadASR/FireRedASR/examples/fireredasr/models/fireredasr_llm.py", line 122, in transcribe encoder_outs, enc_lengths, enc_mask = self.encoder(padded_feat, feat_lengths) File "/opt/homebrew/Caskroom/miniconda/base/envs/fireredasr/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/opt/homebrew/Caskroom/miniconda/base/envs/fireredasr/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl return forward_call(*args, **kwargs) File "/Users/guowenchao/Job/AI/FireRedTeadASR/FireRedASR/examples/fireredasr/models/module/conformer_encoder.py", line 37, in forward enc_output = enc_layer(enc_output, pos_emb, slf_attn_mask=src_mask, File "/opt/homebrew/Caskroom/miniconda/base/envs/fireredasr/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/opt/homebrew/Caskroom/miniconda/base/envs/fireredasr/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl return forward_call(*args, **kwargs) File "/Users/guowenchao/Job/AI/FireRedTeadASR/FireRedASR/examples/fireredasr/models/module/conformer_encoder.py", line 67, in forward out = self.mhsa(out, out, out, pos_emb, mask=slf_attn_mask)[0] File "/opt/homebrew/Caskroom/miniconda/base/envs/fireredasr/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/opt/homebrew/Caskroom/miniconda/base/envs/fireredasr/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl return forward_call(*args, **kwargs) File "/Users/guowenchao/Job/AI/FireRedTeadASR/FireRedASR/examples/fireredasr/models/module/conformer_encoder.py", line 316, in forward attn_scores = matrix_ac + matrix_bd RuntimeError: The size of tensor a (16263) must match the size of tensor b (5000) at non-singleton dimension 3

• ref=/Users/guowenchao/Job/AI/FireRedTeadASR/test_DATA/out/text
• wer.py --print_sentence_wer 1 --do_tn 0 --rm_special 0 --ref /Users/guowenchao/Job/AI/FireRedTeadASR/test_DATA/out/text --hyp /Users/guowenchao/Job/AI/FireRedTeadASR/test_DATA/out/out.txt
• tail -n8 /Users/guowenchao/Job/AI/FireRedTeadASR/test_DATA/out/out.txt.wer

[FireRedTeam]

Audio too long.

https://github.com/FireRedTeam/FireRedASR?tab=readme-ov-file#input-length-limitations