Abraham Owodunni

The link to the Training dataset is attached to the readme is broken https://github.com/davidsandberg/facenet#training-data

Saving and reloading the pretrained model's vocab breaks the tokenizer.

2

**Describe the bug** So I picked [nvidia/parakeet-ctc-0.6b](https://huggingface.co/nvidia/parakeet-ctc-0.6b) and I untarred the the `.nemo` file. After that, I then loaded the model and changed the the vocab this way: **Steps/Code to...

I can't seem to find where the `action: action_deactivate_loop` was created. It was used in the stories file but I can't find its origin.

Too much Latency!

1

I plan on using this for ASR spelling correction but the latency is too much for even the smallest model. Is there a work around or potential solution for this?

Hi, I'm from the future (10 years after this release) and I am stuck with colour quantization. So the Pillow package now has a method to do quantization however the...