nvidia/parakeet-ctc-1.1b 昇腾 NPU 适配

npu-smi 25.5.5
NPU 芯片: Ascend910
HBM 总容量: 65536MB/卡

pip install -r requirements.txt

# 从 hf-mirror.com 拉取
HF_ENDPOINT=https://hf-mirror.com huggingface-cli download nvidia/parakeet-ctc-1.1b --local-dir ./parakeet-ctc-1.1b

# 或从 HuggingFace 直接拉取
huggingface-cli download nvidia/parakeet-ctc-1.1b --local-dir ./parakeet-ctc-1.1b

python inference.py sample.wav --model ./parakeet-ctc-1.1b

import torch
import torch_npu
from transformers import AutoModelForCTC, AutoProcessor

model = AutoModelForCTC.from_pretrained(
    "nvidia/parakeet-ctc-1.1b",
    dtype=torch.bfloat16,
    trust_remote_code=True
).to("npu:0")
model.eval()

processor = AutoProcessor.from_pretrained("nvidia/parakeet-ctc-1.1b", trust_remote_code=True)

# 读取音频
import soundfile as sf
audio, sr = sf.read("sample.wav")

# 推理
inputs = processor(audio, sampling_rate=sr, return_tensors="pt")
input_features = inputs["input_features"].to("npu:0", dtype=torch.bfloat16)
with torch.no_grad():
    logits = model(input_features).logits
predicted_ids = torch.argmax(logits, dim=-1)
text = processor.batch_decode(predicted_ids)[0]
print(text)

python -c "import torch; import torch_npu; print(f'NPU可用: {torch.npu.is_available()}, 设备数: {torch.npu.device_count()}')"

python -c "
from transformers import AutoModelForCTC, AutoConfig
import torch
config = AutoConfig.from_pretrained('./parakeet-ctc-1.1b', trust_remote_code=True)
model = AutoModelForCTC.from_pretrained('./parakeet-ctc-1.1b', config=config, dtype=torch.bfloat16, trust_remote_code=True)
model = model.to('npu:0')
print(f'模型加载成功: {sum(p.numel() for p in model.parameters()):,} 参数')
"

python inference.py test.wav --model ./parakeet-ctc-1.1b

# 在推理过程中查看 NPU 占用
npu-smi info