语音识别阶段出错:[Parakeet-tdt] 500 错误: API服务端内部错误 Error code: 500 - {'details': 'CUDA error: invalid argument CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1 Compile with TORCH_USE_CUDA_DSA to enable device-side assertions. ', 'error': '服务器内部错误'}:
Traceback (most recent call last):
File "videotrans\task\job.py", line 105, in run
File "videotrans\task\_speech2text.py", line 133, in recogn
File "videotrans\recognition\__init__.py", line 230, in run
File "videotrans\recognition\_base.py", line 78, in run
File "videotrans\recognition\_parakeet.py", line 38, in _exec
File "openai\_utils\_utils.py", line 286, in wrapper
File "openai\resources\audio\transcriptions.py", line 406, in create
File "openai\_base_client.py", line 1259, in post
File "openai\_base_client.py", line 1047, in request
openai.InternalServerError: Error code: 500 - {'details': 'CUDA error: invalid argument CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1 Compile with TORCH_USE_CUDA_DSA to enable device-side assertions. ', 'error': '服务器内部错误'}
=
system:Windows-10-10.0.26100-SP0
version:v3.83
frozen:True
language:zh
root_dir:C:/Users/zhu/Downloads/win-videotrans-v3.83