Downloads · 30 days
11
20% of all-time downloads
inoryQwQ/sherpa-onnx-wespeaker-resnet34-ax650
sherpa-onnx-wespeaker-resnet34-ax650 is a audio classification model from inoryQwQ. Use it for the audio classification task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
WeSpeaker ResNet34 speaker embedding model converted to AX650 AXMODEL for on-device speaker verification via sherpa-onnx.
Downloads · 30 days
11
20% of all-time downloads
All-time downloads
54
Public
Repo size
6.8 MB
Likes
0
Public
Click a slice to open those files.
.axmodel6.8 MB · 100%
From the Hugging Face model README
WeSpeaker ResNet34 speaker embedding model converted to AX650 AXMODEL for on-device speaker verification via sherpa-onnx.
| File | Size | Description |
|---|---|---|
wespeaker-resnet34.axmodel | 6.6 MB | AX650 speaker embedding model |
| Metric | Value |
|---|---|
| Cosine Similarity vs ONNX | 0.9973 |
| Max Absolute Error | 0.030 |
| MSE | 0.00011 |
| MACs | 4.5 G |
| ONNX Size (original) | 25 MB |
| AXMODEL Size | 6.6 MB |
| Compression Ratio | 3.8x |
./sherpa-onnx-offline-speaker-identification \
--speaker-model=wespeaker-resnet34.axmodel \
--provider=axera \
test.wav
Apache 2.0