A slice of model.memory_v tensor

Store zeros into block of memory, with aligned AVX store instructions

-************************************ * Common functions **************************************/

resetStream is now deprecated, * prefer initStream() which is more general */

customized variant of memcpy, which can overwrite up to 32 bytes beyond dstEnd * this version copies two times 16 bytes (instead of one time 32 bytes

Operations

Offset the timestamp with mediaTimeOffset to find the time relative to the start of the iSpectrogram buffer, then scale from 100 nanosecond ticks into

<summary>Create a context to transcribe audio with this model</summary> <remarks>Don't call this method, use <see cref="ExtensionMethods.createContext