Modelpublic

inoryQwQ/sherpa-onnx-wenet-ax650

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

0likes6downloads

Model Card

sherpa-onnx-wenet-ax650

WeNet U2++ Conformer CTC Chinese ASR model converted to AX650 AXMODEL for on-device inference via sherpa-onnx.

Model Details

—Original Model: csukuangfj/sherpa-onnx-zh-wenet-aishell
—AXMODEL Source: AXERA-TECH/WeNet encoder
—Architecture: WeNet U2++ Conformer CTC
—Task: Chinese speech recognition (ASR)
—Sample rate: 16000 Hz
—Feature dim: 80-dim mel filterbanks
—Subsampling factor: 4
—Vocabulary size: 4233
—Input: speech (FP32, [1, T, 80]), speech_lengths (INT32, [1])
—Output: CTC log probabilities ctc_log_probs (FP32, [1, T', 4233])
—Target Chip: AX650 (NPU3)
—Quantization: U16 (whole graph)

Files

File	Size	Description
`wenet-encoder.axmodel`	41 MB	AX650 encoder model
`tokens.txt`	-	Vocabulary file (4233 tokens)

Usage with sherpa-onnx

bash

./sherpa-onnx-offline \
  --wenet-ctc-model=wenet-encoder.axmodel \
  --tokens=tokens.txt \
  --provider=axera \
  test.wav

Performance

Metric	Value
ONNX size (original)	138 MB
AXMODEL size	41 MB
Compression ratio	3.4x

Conversion Details

—Pulsar2 Version: 6.0
—Calibration: MinMax with 10 samples
—Quantization: U16

License

Apache 2.0