I’m pretty sure Merlin is computervision, it’s been trained on spectrograms and not actual audio files. I remember years ago when we discussed training a model for audio, the inclusion of time in audio makes things much more complicated.
tiwane
15
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Screenshot from a bird voice identification app as a photo | 8 | 1359 | June 22, 2023 | |
| Audio recordings of bird song/calls | 53 | 4911 | March 10, 2023 | |
| Automatically add a spectrogram view to observations with sounds | 53 | 7028 | September 18, 2025 | |
| Paste image onto observation? | 8 | 523 | September 3, 2024 | |
| Spectrograph allowed? | 5 | 1404 | May 8, 2022 |