speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020 NPU 适配

from modelscope import snapshot_download
model_dir = snapshot_download("iic/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020")

python inference.py

refuse horace vo kingdom ibrahim horace re architectural identities kingdom float peck splendor against rubbed hainanese unequal retention sheriffng consist inquired assemble vo

iic-speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020-NPU/
├── assets/
│   └── test.wav
├── logs/
│   ├── env_check.log
│   ├── inference.log
│   ├── eval_consistency.log
│   └── benchmark.log
├── screenshots/
│   └── self_verification.png
├── models/
├── model_utils.py
├── inference.py
├── eval_consistency.py
├── benchmark.py
├── requirements.txt
├── .gitignore
└── README.md

pip install -r requirements.txt
python inference.py
python eval_consistency.py
python benchmark.py