Method__call__ x : mx.array, shape = (batch_size, <= n_ctx) the text tokens xa : mx.array, shape = (batch_size, n_audio_ctx, n_audio_sta
whisper/mlx_whisper/whisper.py:176
Method__call__(
self,
x,
encoder_x=None,
temb=None,
attn_mask=None,
encoder_
stable_diffusion/stable_diffusion/unet.py:237
Method__call__(
self,
x,
timestep,
encoder_x,
attn_mask=None,
encoder_attn_m
stable_diffusion/stable_diffusion/unet.py:403