update readme

README.md

@@ -112,6 +112,21 @@ This repo contains the following configurations under `./models/`:
     * The output quality itself leaves a lot to be desired.
   * Training is finalized with this model, as dedicated training time to the base model to extend it for NAR-len capabilities is optimal, but these weights will exist for who it may concern.
 
+* `nemo-smaller-44khz-llama-8` / `nemo-larger-44khz-llama-8`: Fully non-autoregressively, fully parallel models.
+  * These models utilize:
+    * a new implementation that aims to operate on *all* codebook levels instead of one codebook level at a time.
+    * `nvidia/audio-codec-44khz` as the audio codec used for 44KHz audio instead of EnCodec for 24KHz.
+      * `descript-audio-codec` can be revisited as an RVQ-based codec since they're easier to train a model around over an FSQ codec
+      * an EnCodec variant can also be revisited, as it's rather quick to get a model to have speech emerge
+  * At the moment, it doesn't seem to offer any benefits over the reference model.......
+    * Zero-shot performance / speaker similarity is piss poor
+      * More training is required, but I ***suppose*** these models can be used to finetune on a speaker for the meantime
+      * The `proms_emb` might be weak compared to the `resps_emb`. I'm not sure of the best remedy for this.
+    * Actual audio quality doesn't seem all that apparent
+      * I imagine a post-training step similar to RLHF with actual 44KHz audio rather than upsampled-from-24KHz audio could fix this
+    * The `smaller` model has the same inference speed as the `larger` model on my V100
+      * This could either simply be because a V100 doesn't benefit from a narrow model, or there's a bottleneck elsewhere
+
 Some additional configurations have been explored with, but experiments have not been fruitful:
 * Exotic wrappers like `BitNet` seemed to yield little gains in inferencing, somehow. The memory savings is pretty much unneccessary as the models are already manageable at ~200M parameters.
 * Mamba / Mamba2-based models have shown that it's ***really*** hard to have an AR+NAR model. I really do not want to bother throwing the compute at another ~~meme~~ arch I can't easily make use of all the other tech to throw at.