Downloads · 30 days
7
16% of all-time downloads
inoryQwQ/sherpa-onnx-paraformer-ax650
sherpa-onnx-paraformer-ax650 is a automatic speech recognition model from inoryQwQ. Use it when you need speech turned into text. The card lists the license as apache-2.0.
Paraformer-large-Chuan Chinese ASR model converted to AX650 AXMODEL for on-device inference via sherpa-onnx.
Downloads · 30 days
7
16% of all-time downloads
All-time downloads
43
Public
Repo size
235 MB
Likes
0
Public
Click a slice to open those files.
.axmodel235 MB · 100%
From the Hugging Face model README
Paraformer-large-Chuan Chinese ASR model converted to AX650 AXMODEL for on-device inference via sherpa-onnx.
| File | Precision | Size | Description |
|---|---|---|---|
encoder-5-seconds.axmodel | INT8 | 165 MB | Encoder [1,83,560]→[1,83,512] |
predictor-5-seconds.axmodel | INT8 | 831 KB | Predictor [1,83,512]→[1,83] |
decoder-5-seconds.axmodel | INT8 | 60 MB | Decoder [1,83,512]×3→[1,83,8404] |
| Metric | Value |
|---|---|
| RTF | 0.007 |
| Pulsar2 Version | 6.0 (commit 48520c11) |
./sherpa-onnx-offline \
--tokens=tokens.txt \
--paraformer=encoder-5-seconds.axmodel,predictor-5-seconds.axmodel,decoder-5-seconds.axmodel \
--provider=axera \
audio.wav
Apache 2.0