---
license: apache-2.0
language:
- en
base_model:
- csukuangfj/sherpa-onnx-zipformer-ctc-en-2023-10-02
pipeline_tag: automatic-speech-recognition
datasets:
- librispeech
metrics:
- wer
tags:
- sherpa-onnx
- axera
- ax650
- axmodel
- zipformer
- ctc
- asr
- speech-recognition
- english
- pulsar2
---

# sherpa-onnx-zipformer-ctc-en-ax650

Zipformer CTC English ASR model converted to AX650 AXMODEL for on-device inference via sherpa-onnx.

## Model Details

- **Original Model**: [csukuangfj/sherpa-onnx-zipformer-ctc-en-2023-10-02](https://hf-mirror.com/csukuangfj/sherpa-onnx-zipformer-ctc-en-2023-10-02)
- **Architecture**: Zipformer2 CTC
- **Task**: English speech recognition (ASR)
- **Sample rate**: 16000 Hz
- **Feature dim**: 80-dim mel filterbank
- **Frame shift**: 10ms
- **Subsampling factor**: 4
- **Vocabulary size**: 500
- **Target Chip**: AX650 (NPU3)
- **Quantization**: U16 (int16)

## Files

| File | Size | Description |
|------|------|-------------|
| `zipformer-ctc.axmodel` | 73 MB | AX650 compiled model |
| `tokens.txt` | 5 KB | 500 output tokens |

## Input / Output

- **Input**: `x` [1, 512, 80], `x_lens` [1] — 512 frames (~5.12s @ 16kHz)
- **Output**: `log_probs` [1, 126, 500] — CTC log probabilities

## Usage with sherpa-onnx

```bash
./sherpa-onnx-offline \
  --zipformer-ctc-model=zipformer-ctc.axmodel \
  --tokens=tokens.txt \
  --provider=axera \
  audio.wav
```

## Known Limitations

- Fixed input frame length (T=512); shorter inputs must be padded
- Output log_probs length determined by subsampling_factor=4

## Conversion Details

- **Pulsar2 Version**: 6.0
- **Input Shape**: `x` [1, 512, 80], `x_lens` [1]
- **Calibration**: MinMax with 10 random mel features
- **Quantization**: U16

## License

Apache 2.0