RuntimeError: Unable to find a valid cuDNN algorithm to run convolution

[JamisonMurphy]

I have a RTX 3060 laptop 6G ,but when i try to whisper a 3min video :

C:\Users\chengzi\Downloads\Video>whisper 666.flv --language zh --model medium
Traceback (most recent call last):
File "C:\Users\chengzi\AppData\Roaming\Python\Python310\Scripts\whisper-script.py", line 33, in
sys.exit(load_entry_point('openai-whisper==20230124', 'console_scripts', 'whisper')())
File "C:\Users\chengzi\AppData\Roaming\Python\Python310\site-packages\whisper\transcribe.py", line 311, in cli
result = transcribe(model, audio_path, temperature=temperature, **args)
File "C:\Users\chengzi\AppData\Roaming\Python\Python310\site-packages\whisper\transcribe.py", line 181, in transcribe
result: DecodingResult = decode_with_fallback(segment)
File "C:\Users\chengzi\AppData\Roaming\Python\Python310\site-packages\whisper\transcribe.py", line 117, in decode_with_fallback
decode_result = model.decode(segment, options)
File "C:\Program Files\Python\Python310\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "C:\Users\chengzi\AppData\Roaming\Python\Python310\site-packages\whisper\decoding.py", line 705, in decode
result = DecodingTask(model, options).run(mel)
File "C:\Program Files\Python\Python310\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "C:\Users\chengzi\AppData\Roaming\Python\Python310\site-packages\whisper\decoding.py", line 621, in run
audio_features: Tensor = self._get_audio_features(mel) # encoder forward pass
File "C:\Users\chengzi\AppData\Roaming\Python\Python310\site-packages\whisper\decoding.py", line 565, in _get_audio_features
audio_features = self.model.encoder(mel)
File "C:\Program Files\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\chengzi\AppData\Roaming\Python\Python310\site-packages\whisper\model.py", line 149, in forward
x = F.gelu(self.conv1(x))
File "C:\Program Files\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Program Files\Python\Python310\lib\site-packages\torch\nn\modules\conv.py", line 307, in forward
return self._conv_forward(input, self.weight, self.bias)
File "C:\Users\chengzi\AppData\Roaming\Python\Python310\site-packages\whisper\model.py", line 43, in _conv_forward
return super()._conv_forward(
File "C:\Program Files\Python\Python310\lib\site-packages\torch\nn\modules\conv.py", line 303, in _conv_forward
return F.conv1d(input, weight, bias, self.stride,
RuntimeError: Unable to find a valid cuDNN algorithm to run convolution

[JamisonMurphy]

how to decrease batch size ,I need to modify source code?