aoom

Transformer Quality in Linear Time Weizhe Hua, Zihang Dai, Hanxiao Liu, Quoc V. Le We revisit the design choices in Transformers, and propose methods to address their weaknesses in handling...

~/whisper.cpp-master$ ./main -m qqml-tiny-q5_1.bin -f ./samples/jfk.wav -pc --no-gpu whisper_init_from_file_with_params_no_state: loading model from 'qqml-tiny-q5_1.bin' whisper_init_with_params_no_state: use gpu = 0 whisper_init_with_params_no_state: flash attn = 0 whisper_init_with_params_no_state: gpu_device = 0 whisper_init_with_params_no_state: dtw =...

The python version requirement has become a major problem for many devices that don't work.

6

The default python version for many devices does not meet exo's expectations. Updating python causes a host of other problems. If the dependency on python version could be reduced, exo...