cvillela

Results 10 comments of cvillela

command-line non-interactive possible?

Would be great!

how to start to train using "dora grid" when I do not have a cluster

Same question here!

how to start to train using "dora grid" when I do not have a cluster

Hey @Liujingxiu23 did you find a workaround for this?

RuntimeError: Error(s) in loading state_dict for LatentDiffusion: Unexpected key(s) in state_dict: "cond_stage_model.model.text_branch.embeddings.position_ids".

I am facing the exact same error when trying to load the model within a conda environment created by following README. The error is the same when using both "audioldm-m-full.ckpt"...

24bit FLAC shown as 32 bits per sample

Same issue

Fix audio segment export bigger 4gb

Any help on this? I am facing the exact same issue.....

Add Support for large audio files ( > 2GB)

> I have now made another modification to audio_segment.py: I added a pull request #734, which in case the AudioSegment is bigger than 4 GB, exports into separate temporary WAV...

Add Support for large audio files ( > 2GB)

For now will keep saving chunks and joining them, or use `soundfile.write()` which handles this!

Fewer than expected results were retrieved during querying the index

Hello @markkohdev! I am facing the exact same issue. Some calls for querying for N neighbors in an index of length N results in this error. My objective would be...

Fewer than expected results were retrieved when querying for len(index) items

Hey @dylanrb123 , thank you very much for the response and sorry for the delay. I am building an implementation of K-Means clustering with the Voyager library. An heuristic approximation...