Dmitry Grankin
Dmitry Grankin
Feature requests should first be proposed on [the forum](https://forums.fast.ai). **Link to forum discussion.** https://forums.fast.ai/t/tabular-categorical-classes-for-out-of-memory-datasets/79366 **Is your feature request related to a problem? Please describe.** I am training with tabular dataset...
I am not sure if it is an issue with px or jupyterlab or my particular configuration, but my jupyterlab `px.scatter` output cells height are limited to pretty narrow, while,...
Hi, though I see[ this issue](https://github.com/nurdtechie98/drive-cli/issues/77) has been fixed, I still experience it. It happens while doing `drive add_remote` I would appreciate an advice. ` File "/home/dima/drive-cli/drive_cli/actions.py", line 178, in...
Hey, while inspecting the compiled save json I was expecting to see the compiled prompts. I can see only "demos" and other fields just empty. I am confused since the...
Hey, I have been using function calling through llamaindex and langchain to delivere structured output. Can you give a hint on how to implement this in dspy?
following to Feature Request: Implementing Persistent Speaker Embeddings Across Conversations #227
Hey @juanmc2005, Following to the issue #227, - I have implemented speaker centroids as list of embeddings without mapping, assuming speaker_0 == centroid 0 inside SpeakerDiarization - added a better...
It looks like pipeline quickly forgets previous speakers, assigning wrong tags to new ones, so that a conversation of 4-5 people being inferenced as a conversation of 2. I am...
### Feature Description I propose the addition of a feature to the DIART project that allows for the persistence and reuse of speaker embeddings across multiple conversations. I am willing...