Downloads · 30 days
4
7% of all-time downloads
sherpa-onnx-ced-mini-ax650
inoryQwQ/sherpa-onnx-ced-mini-ax650
sherpa-onnx-ced-mini-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.
CED (CNN-based Encoder-Decoder) audio tagging model converted to AX650 AXMODEL for on-device inference via sherpa-onnx. Detects 527 AudioSet event classes.
All-time downloads
55
Public
Repo size
11.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.axmodel11.8 MB · 99%
At a glance
- Task
- Audio Classification
- License
- apache-2.0
- Model type
- sherpa-onnx-axmodel
- Access
- Public
- Created
- Jul 14, 2026
- Updated
- Jul 17, 2026
- SHA
- d0e116c3
Base models
Model card
From the Hugging Face model README
sherpa-onnx-ced-mini-ax650
CED (CNN-based Encoder-Decoder) audio tagging model converted to AX650 AXMODEL for on-device inference via sherpa-onnx. Detects 527 AudioSet event classes.
Model Details
- Original Model: k2-fsa/sherpa-onnx-ced-mini-audio-tagging-2024-04-19
- Architecture: CED (CNN-based Encoder-Decoder) - ConvNeXt style
- Task: Audio tagging (527 AudioSet event classes)
- Input: 64-dim mel-spectrogram features, up to 1001 frames (~10s @ 16kHz)
- Output: 527-class event probabilities
- Target Chip: AX650 (NPU3)
- Quantization: U16 (MinMax calibration)
Files
| File | Size | Description |
|---|---|---|
ced-mini.axmodel | 11.2 MB | AX650 compiled model |
class_labels_indices.csv | - | 527 AudioSet class labels |
test.wav | - | Sample test audio |
Performance (AX650)
| Metric | Value |
|---|---|
| RTF | 0.007 |
| Top-1 Accuracy vs ONNX | 100% |
| Top-5 Accuracy vs ONNX | 60% |
| Max Absolute Error vs ONNX | 0.035 |
| ONNX Size (original) | 37 MB |
| AXMODEL Size | 11.2 MB |
| Compression Ratio | 3.3x |
Tested on AX650 NPU3 with 3-second 16kHz mono audio.
Usage with sherpa-onnx
./sherpa-onnx-offline-audio-tagging \
--ced-model=ced-mini.axmodel \
--labels=class_labels_indices.csv \
--provider=axera \
test.wav
Or via Python:
import sherpa_onnx
config = sherpa_onnx.AudioTaggingConfig()
config.model.ced = "ced-mini.axmodel"
config.model.provider = "axera"
config.labels = "class_labels_indices.csv"
tagger = sherpa_onnx.AudioTagging(config)
stream = tagger.create_stream()
stream.accept_waveform(16000, samples)
results = tagger.compute(stream)
Conversion Details
- Pulsar2 Version: 6.0 (48520c11)
- Input Shape: [1, 64, 1001]
- Calibration: 10 random mel-spectrogram samples
License
Apache 2.0
- Task
- Audio Classification
- Type
- sherpa-onnx-axmodel
- License
- apache-2.0
- Languages
- en
- Created
- Jul 14, 2026
- Updated
- Jul 17, 2026