RuntimeError: Cannot execute emptyCache() without MPS backend.

[Lzzzii10]

2024-11-29 11:40:37,152 - STT.paraformer_handler - DEBUG - infering paraformer...
0%| | 0/1 [00:00<?, ?it/s]/root/anaconda3/envs/speechtospeech/lib/python3.10/site-packages/funasr/models/paraformer/model.py:251: FutureWarning: torch.cuda.amp.autocast(args...) is deprecated. Please use torch.amp.autocast('cuda', args...) instead.
with autocast(False):
rtf_avg: 0.280: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 2.26it/s]
Exception in thread Thread-5 (run):
Traceback (most recent call last):
File "/root/anaconda3/envs/speechtospeech/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/root/anaconda3/envs/speechtospeech/lib/python3.10/threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "/ai/app/voicechat/speech-to-speech/baseHandler.py", line 37, in run
for output in self.process(input):
File "/ai/app/voicechat/speech-to-speech/STT/paraformer_handler.py", line 56, in process
torch.mps.empty_cache()
File "/root/anaconda3/envs/speechtospeech/lib/python3.10/site-packages/torch/mps/init.py", line 85, in empty_cache
torch._C._mps_emptyCache()
RuntimeError: Cannot execute emptyCache() without MPS backend.
^CException ignored in: <module 'threading' from '/root/anaconda3/envs/speechtospeech/lib/python3.10/threading.py'>
Traceback (most recent call last):
File "/root/anaconda3/envs/speechtospeech/lib/python3.10/threading.py", line 1567, in _shutdown
lock.acquire()
KeyboardInterrupt: