modelscope-funasr这个问题怎么解决？
modelscope-funasr这个问题怎么解决？环境安装：
python==3.7.13
torch==1.13.1+cu113
funasr==1.0.15
使用模型：
https://www.modelscope.cn/models/damo/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary
参考示例：
https://github.com/alibaba-damo-academy/FunASR/blob/5e7eb6f160c48861cbcd39825a0cb98f98538772/examples/industrial_data_pretraining/seaco_paraformer/finetune_from_local.sh
完整错误：
Traceback (most recent call last):
File "../../../funasr/bin/train.py", line 42, in main_hydra
main(kwargs)
File "../../../funasr/bin/train.py", line 192, in main
trainer.run()
File "/code/zhili_test/new/FunASR-main/funasr/train_utils/trainer.py", line 181, in run
self._train_epoch(epoch)
File "/code/zhili_test/new/FunASR-main/funasr/train_utils/trainer.py", line 245, in _train_epoch
retval = self.model(batch)
File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(input, **kwargs)
File "/opt/conda/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 1040, in forward
output = self._run_ddp_forward(inputs, kwargs)
File "/opt/conda/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 1000, in _run_ddp_forward
return module_to_run(*inputs[0], kwargs[0])
File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(input, *kwargs)
File "/code/zhili_test/new/FunASR-main/funasr/models/seaco_paraformer/model.py", line 120, in forward
assert text_lengths.dim() == 1, text_lengths.shape
AssertionError: torch.Size([32, 1])
-
阿里云大降价~
根据您提供的错误信息，问题出现在
funasr/models/seaco_paraformer/model.py的第120行。错误提示是AssertionError: torch.Size([32, 1])，意味着text_lengths的形状应该是一维的，但实际上是二维的。要解决这个问题，您可以尝试修改
funasr/models/seaco_paraformer/model.py文件的第120行，将assert text_lengths.dim() == 1改为assert text_lengths.dim() == 2。这样，代码将接受二维的text_lengths输入。请注意，这只是一个临时解决方案，可能会影响到其他部分的功能。建议您在修改之前备份原始文件，并在修改后进行充分的测试以确保不会引入其他问题。
2024-03-27 19:02:27赞同 展开评论
