funasr_seaco_paraformer_onnx_with_timestamp - 昇腾NPU适配

┌──────────────────────────────────────────────────┐
│                   Inference Pipeline              │
├──────────┬──────────────┬────────────────────────┤
│  Audio   │  Frontend    │  ONNX Runtime          │
│  (.wav)  │  (FBank)     │  ┌──────────────┐      │
│ ────────▶│  Feature     │  │ CPU EP (基线) │      │
│          │  Extraction  │──┤              ├──▶ ASR
│          │  + CMVN      │  │ CANN EP (NPU) │      │
│          │  + LFR       │  └──────────────┘      │
│          │  + Hotword   │  Model: model.onnx     │
│          │  Embedding   │  or model_quant.onnx   │
└──────────┴──────────────┴────────────────────────┘

# 1. 安装基础依赖
pip install numpy scipy soundfile onnx onnxruntime

# 2. 安装 CANN 支持的 ONNX Runtime (有预编译包则直接安装)
pip install onnxruntime-cann

# 3. 安装 funasr_onnx (可选，用于CPU基线对比)
pip install funasr_onnx

# 4. 下载模型
pip install modelscope
modelscope download --model QuadraV/funasr_seaco_paraformer_onnx_with_timestamp

# 检查 NPU 状态
npu-smi info

# 检查 CANN 版本
cat /usr/local/Ascend/ascend-toolkit/latest/version.cfg 2>/dev/null || \
cat /usr/local/Ascend/cann-*/version.cfg

# 验证 ONNX Runtime CANN EP
python3 -c "import onnxruntime; print(onnxruntime.get_available_providers())"
# 期望输出包含: ['CANNExecutionProvider', 'CPUExecutionProvider', ...]

pip install modelscope
modelscope download --model QuadraV/funasr_seaco_paraformer_onnx_with_timestamp

funasr_seaco_paraformer_onnx_with_timestamp/
├── model.onnx              # 全精度模型 (~913MB)
├── model_quant.onnx        # 量化模型 (~329MB)
├── model_eb.onnx           # 编码器模型
├── model_eb_quant.onnx     # 量化编码器模型
├── config.yaml             # 模型配置
├── configuration.json      # 框架配置
├── tokens.json             # 词表
├── seg_dict                # 分词词典
├── am.mvn                  # CMVN归一化参数
├── lm/                     # 语言模型
│   ├── lm.pb
│   └── lm.yaml
├── example/                # 示例音频
│   ├── asr_example.wav
│   └── hotword.txt
└── README.md               # 原始README

# 使用 inference.py
python3 inference.py \
    --wav ~/.cache/modelscope/hub/models/QuadraV/funasr_seaco_paraformer_onnx_with_timestamp/example/asr_example.wav \
    --backend cpu

# 使用 seaco_paraformer_npu.py (funasr_onnx 兼容接口)
python3 seaco_paraformer_npu.py \
    --wav ~/.cache/modelscope/hub/models/QuadraV/funasr_seaco_paraformer_onnx_with_timestamp/example/asr_example.wav \
    --device cpu

[
  {
    "preds": "欢迎大家来到么哒社区进行体验",
    "timestamp": [
      [890, 1190], [1190, 1510], [1510, 1730], [1730, 1910],
      [1910, 2070], [2070, 2330], [2330, 2470], [2470, 2750],
      [2750, 2950], [2950, 3290], [3290, 3470], [3470, 3810],
      [3810, 4010], [4010, 4245]
    ],
    "raw_tokens": ["欢", "迎", "大", "家", "来", "到", "么", "哒", "社", "区", "进", "行", "体", "验"]
  }
]

# NPU 推理 (ONNX Runtime CANN EP)
python3 inference.py \
    --wav ~/.cache/modelscope/hub/models/QuadraV/funasr_seaco_paraformer_onnx_with_timestamp/example/asr_example.wav \
    --backend npu_ort

# 使用量化模型 + NPU
python3 inference.py \
    --wav ~/.cache/modelscope/hub/models/QuadraV/funasr_seaco_paraformer_onnx_with_timestamp/example/asr_example.wav \
    --backend npu_ort \
    --quantize

# 将 ONNX 转换为 Ascend OM 格式
python3 inference.py --convert \
    --model_dir ~/.cache/modelscope/hub/models/QuadraV/funasr_seaco_paraformer_onnx_with_timestamp

# 或直接使用 atc 命令
atc --model=model.onnx \
    --framework=5 \
    --output=model \
    --soc_version=Ascend910 \
    --input_shape="speech:1,-1,560;speech_lengths:1;bias_embed:1,1,512" \
    --input_format=ND

# 自动对比 CPU vs NPU 精度
python3 inference.py \
    --wav ~/.cache/modelscope/hub/models/QuadraV/funasr_seaco_paraformer_onnx_with_timestamp/example/asr_example.wav \
    --compare \
    --output accuracy_report.json

# 多文件评测
python3 benchmark.py \
    --wav ~/.cache/modelscope/hub/models/QuadraV/funasr_seaco_paraformer_onnx_with_timestamp/example/asr_example.wav \
    --output benchmark_report.json

============================================================
  Accuracy Report
============================================================
  NPU Available:   True
  SoC Version:     ascend910_9391
  CPU Time:        0.1158s
  NPU Time:        1.6100s (含CPU→NPU数据传输开销)
  Text Match:      True
  TS Max Diff:     0.00ms
  TS Mean Diff:    0.00ms
  TS Error %:      0.00%
  Accuracy Passed: True
============================================================

python3 benchmark.py \
    --wav <test.wav> \
    --warmup 3 \
    --runs 10 \
    --output benchmark_report.json

# 确认已安装 onnxruntime-cann
pip list | grep onnxruntime-cann

# 如果未安装，检查是否有预编译包或从源码构建
# 参考: https://www.hiascend.com/document/detail/zh/canncommercial/80RC1/

@article{gao2023seaco,
  title={SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Ability},
  author={Gao, Zhifu and Zhang, Shiliang and Lei, Ming and McLoughlin, Ian},
  journal={arXiv preprint arXiv:2308.00000},
  year={2023}
}

@misc{funasr2023,
  title={FunASR: A Fundamental End-to-End Speech Recognition Toolkit},
  author={FunASR Team},
  year={2023},
  publisher={GitHub},
  howpublished={\url{https://github.com/modelscope/FunASR}},
}