funasr使用qwen-audio支持双卡进行测试？

[lai-serena]

❓ Questions and Help

如果使用单卡，T4会出现OOM，我有多张T4卡，应该怎么修改才可以使用多卡呢？

Code

from funasr import AutoModel

model = AutoModel(model="Qwen-Audio",
                  model_path="models/Qwen-Audio"
                  )

audio_in = "39937061.wav"

# 1st dialogue turn
prompt = '这个内容是什么?'
cache = {"history": None}
res = model.generate(input=audio_in, prompt=prompt, cache=cache)
print(res)

• OS (e.g., Linux):
• FunASR Version (e.g., 1.0.0):
• ModelScope Version (e.g., 1.11.0):
• PyTorch Version (e.g., 2.0.0):
• How you installed funasr (pip, source):
• Python version:
• GPU 3张T4
• CUDA/cuDNN version (e.g., cuda11.7):
• Docker version (e.g., funasr-runtime-sdk-cpu-0.4.1)
• Any other relevant information: