2 Apr
2022
2 Apr
'22
3:16 p.m.
i think i'll try making there be 2 models first. i did that a little and am still working on it. the detokenization function doesn't yet do batching, it seems. i also enabled raw bytes so the model can theoretically produce all words, but it will eat into the capacity of the model if there are too many new ones during training. this would mean another finetuning cycle would be needed. don't remember if that's planned. but could work around it by uhhhh not using random data, rather using samples from the recording in question. right. the original model produces letters described as words. this is not correct. but isn't what the current focus is. when this is addressed later it may resolve some or all of these partial concerns.