CSM-1B Ascend NPU 适配

# 基础依赖
pip install torch==2.9.0 torch_npu transformers>=5.0.0

# 音频处理
pip install scipy soundfile numpy

# 模型下载
pip install modelscope
modelscope download --model sesameAILabs/csm-1b

import torch
import torch_npu
from transformers import AutoProcessor, CsmForConditionalGeneration
import scipy.io.wavfile as wavfile
import numpy as np

# 加载模型
model_path = "/path/to/csm-1b"
processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
model = CsmForConditionalGeneration.from_pretrained(
    model_path,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
)

# 移到 NPU
device = torch.device("npu:0")
model = model.to(device)
model.eval()

# 使用 Chat Template 构建输入
text = "Hello, this is CSM-1B running on Ascend NPU."
conversation = [{"role": "0", "content": [{"type": "text", "text": text}]}]
inputs = processor.apply_chat_template(conversation, tokenize=True, return_dict=True)
inputs = inputs.to(device)

# 生成语音
with torch.no_grad():
    output = model.generate(**inputs, max_new_tokens=512, do_sample=True, output_audio=True)

# 获取音频
audio = output[0] if isinstance(output, list) else output.audio[0]

# 保存音频
audio_np = audio.cpu().float().numpy()
wavfile.write("output.wav", 24000, np.clip(audio_np, -1, 1).astype("float32"))

# 基础推理
python inference.py --text "Hello from Ascend NPU" --output output.wav

# 运行所有评测
python inference.py --all

# 仅精度评测
python eval_accuracy.py

# 仅性能测试
python eval_performance.py

csm-1b/
├── inference.py              # 主推理脚本
├── eval_accuracy.py          # 精度评测脚本
├── eval_performance.py       # 性能基准测试
├── run_all.sh                # 一键评测流水线
├── README.md                 # 本文档
├── output/                   # 输出目录
│   ├── accuracy_evaluation.json
│   ├── accuracy_summary.txt
│   ├── performance_benchmark.json
│   └── performance_summary.txt
└── model/                    # 模型文件 (需下载)

@misc{sesame2025csm,
  title={CSM-1B: A Conversational Speech Generation Model},
  author={Sesame AI Labs},
  year={2025},
  publisher={HuggingFace},
  howpublished={\url{https://huggingface.co/sesame/csm-1b}},
}