YAMNet (ONNX), mirrored for Rostrum
Google's YAMNet sound event classifier (521 AudioSet classes: speech, dog bark, rain, guitar, applause ...), as a tf2onnx ONNX export, with its class map.
This repository is a pinned, public copy of the exact files the Rostrum apps download. Rostrum fetches each file at a fixed commit of this repository and checks its SHA-256 before use.
What Rostrum uses it for
Sound's tags and its sound library's search: it names what is heard in a sound and when. It only listens.
Rostrum uses it for analysis only, never generation: it reads what is in a recording or a picture and makes no new sound, voice or image.
Files
| File | Bytes | SHA-256 |
|---|---|---|
yamnet.onnx |
16,093,603 | 1510041dce24a2e9e84ec546807ac408ae496da6d1ed41bc3ccba649623f8e19 |
yamnet_class_map.csv |
14,096 | cdf24d193e196d9e95912a2667051ae203e92a2ba09449218ccb40ef787c6df2 |
In Rostrum's models folder they go under yamnet/.
Source
| What | Where | Commit / version |
|---|---|---|
| Exact files (unchanged copy) | https://huggingface.co/zeropointnine/yamnet-onnx | ac2ca3bd45d12ec1f19f1144205ea529b4e9dedf |
| Original code, Google | https://github.com/tensorflow/models/tree/master/research/audioset/yamnet | 8f3b2e48fff92a7fa8d504908b51a6eb51e868a0 (master when mirrored) |
| Original weights, Google | https://www.kaggle.com/models/google/yamnet | version 1 |
Authors
Google (YAMNet code, weights and the AudioSet ontology); zeropointnine (ONNX export).
Licence
YAMNet code and weights are Apache-2.0 (LICENSE). The class names in yamnet_class_map.csv come from the AudioSet ontology, CC BY-SA 4.0 (LICENSE-class-map), by Google; they are shared unchanged under the same licence. Files redistributed unchanged.