Jeffrey Wardman

@bmabey Randomly sampling within the dataloader for multiple images. Would be nice to augment labels as well. These can then be fed in with ``` AUGMENTATION = MIXUP(p=0.6) # Second...

Thanks for linking the preexisting issue. I missed it; my apologies. Surely there's a simple way to add a filter=* argument that will skip attempting to download files that don't...

```python import torch from transformers import WhisperProcessor, WhisperForConditionalGeneration from datasets import load_dataset from transformers import AutoProcessor, AutoModelForCTC def inference(input, processor, model): output = processor(input, sampling_rate=16000, return_tensors="pt") if "whisper" in processor.tokenizer_class.lower():...

You can see in the above that the transcript is gibberish for the unscaled whisper model. This is because it is taking in as input the range [0, 65535] rather...

This approach with DTW is more memory efficient and scalable: https://github.com/linto-ai/whisper-timestamped

Just going to bump this. There are several solutions out there and this is a pretty key missing feature from the transformer implementation of Whisper. E.g. https://github.com/jianfch/stable-ts/blob/main/stable_whisper/whisper_word_level.py

@jongwook is there a way to access it via a beta flag for instance? How can we know when something is/isn't added to the API?

Unfortunately neither solution is suitable for me. The former really struggles with curves and creates a lot of triangles that look like dents. The latter takes far too long (to...

Do you have a link for the issue in VTK's GItLab repository? Is there a way to allow decimate to return the removed/remaining point indices? That would resolve the issue....

No worries. I cannot reproduce it with the mesh in the example below. I shared with you privately a link to an open source dataset. This is the code: ```...