Spaces:

natasa365
/

whisper.cpp

Running

whisper.cpp / ggml-cuda.cu

Kawrakow

CUDA: faster dequantize kernels for Q4_0 and Q4_1 (llama/4938)

73c6598 unverified almost 2 years ago

425 kB

File too large to display, you can check the raw version instead.