-
I just attended Weekend at Sapsucker Woods and spoke with Lea Bouffaut about BirdNet. I have 5 TB of bat data from Loudoun County VA and would like to make a classifier for our local bats. The comme…
-
Hi, I got the error called `RuntimeError: Expected 2D (unbatched) or 3D (batched) input to conv1d, but got input of size: [1, 926, 80, 2]`. I wonder how I can fix it. Thanks.
-
### System Info
Hi, I have found huge memory consumption on my WhisperForAudioClassification model even when I supplied small audios, turns out WhisperFeatureExtractor always pads features to 30s chu…
-
First spectrum comparison for ADPCM, on commit fbb89f0
- the ac coupling in the PCB has a high pass effect visible in the spectrum, with 10Hz signals more attenuated than in the core. Not critical …
-
Hi @NickleDave and everyone,
It's me again, sorry. I ran into a `torch.cuda.OutOfMemoryError` when I was running `vak predict` on my dataset. Please find below the error message:
```
2024-02-27 17…
-
__Proposal:__
Create a function that provides local frequency given a series of oscillating data.
__Current behavior:__
There's not an easy way to estimate the component frequencies/amplitudes …
-
**Describe the bug**
I used the sample code from the Readme.md file to create this test. I have a sample reference .wav file (about 2 seconds). I added this file to the modelService. Then I played…
-
Stuff to do to get started:
- [ ] [Theory of Audio for ML](https://www.youtube.com/watch?v=iCwMQJnKk2c&list=PL-wATfeyAMNqIee7cH3q1bh4QJFAaeNv0). Most important topics from the series are:
* Sou…
-
To allow flexibility in the number of channels (other than 1, 3 for greyscale vs RGB) we should go directly from Spectrograms to Tensors. Augmentations that currently happen on images can easily be mo…
-
the bug is described at pytorch/examples#148. I just wonder if this is a bug in PyTorch itself, as the example code looks clean to me. Also, I wonder if this is related to #1120.