-
This is considered best practice for ML libraries and allows all the configuration parameters to be located and changed in one file without changing the code.
-
I originally asked this question at Stack Exchange Bioacoustics, which suggested that I ask here.
BirdNET output in the Raven Pro format includes a column titled "Channel", which is _always_ popula…
-
@sdenton4 has uploaded separated a2o embeddings to GCS (gs://a20_dropbox/one_percent_sep_embeddings). These are pretty much same as the earlier embeddings but they now have 5 more channels (and 5x inc…
-
To enabled https://github.com/developmentseed/bioacoustics-frontend/issues/125, the API should have a method to store the search audio in a storage account. Ideally we can make this an optional featur…
-
@willemarcel could we add support to proxy the https://api.acousticobservatory.org/audio_recordings/ endpoint? This is required to download the search results for subsequent search https://github.com/…
-
With the change on the frontend to fetch all results (progressively), I'm noticing a few different bottlenecks on the backend. One is that we repeatedly call the embed service for each search for the …
-
Users want to be able to select an audio file by dropping the file into the application.
Requirements:
- The label reads "Drag and drop audio file here, or click to select from your device"
- …
-
When results are returned, the frontend should be able to filter results by unique recordings. This will permit the view of results where only the result with the lowest similarity distance for each r…
-
- As discussed in #5
- [ ] I think we want to have an explicit module `vocalpy.segment` that further contains methods grouped by the schema of Kemp et al 2000: energy-based methods, metric-based meth…
-
When there are many requests from the frontend at the same time, I'm seeing this in the API logs:
```
Traceback (most recent call last):
File "/usr/local/lib/python3.9/site-packages/django/core…