search

Tele-AI / TeleSpeech-ASR

388 stars 37 forks source link

如何不使用CUDA运行 #31

Open GaoZhipengCN opened 2 weeks ago

GaoZhipengCN commented 2 weeks ago

./decode.sh INFO:main:import user_dir: /Users/gao/TeleSpeech-ASR/data2vec_dialect Traceback (most recent call last): File "/Users/gao/TeleSpeech-ASR/data2vec_dialect/run_scripts/../infer.py", line 464, in hydra_main distributed_utils.call_main(cfg, main) File "/Users/gao/fairseq/fairseq/distributed/utils.py", line 404, in call_main main(cfg, **kwargs) File "/Users/gao/TeleSpeech-ASR/data2vec_dialect/run_scripts/../infer.py", line 408, in main raise ValueError("CUDA not found; set cpu=True to run without CUDA") ValueError: CUDA not found; set cpu=True to run without CUDA

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.

TTTdas commented 2 weeks ago

在执行decode.sh脚本中，添加一行common.cpu=true \

GaoZhipengCN commented 2 weeks ago

谢谢，已解决。 通过在infer.py中的def main(cfg: InferConfig) -> float:开头添加cfg.common.cpu = True