seamless-m4t-v2-large transformers 使用gpu推理

2023-12-18 11:35:02

GPU version:

step 1, model???? = model.to('cuda:0')???? or? model???? = model.to('cuda')

step2:? audio_inputs = processor(audios=audio, return_tensors="pt").to('cuda:0')? or audio_inputs = processor(audios=audio, return_tensors="pt").to('cuda')

CPU version:

step 1 not valid for cpu , so marked this line,???? #model???? = model.to('cuda:0')???? or? model???? = model.to('cuda')

step2:? audio_inputs = processor(audios=audio, return_tensors="pt")

records:

推理3s的音频转音频性能对比， rtx4090 vs cpu 11870

rtx4090:? 0.5s

cpu 11870:? 3.25s

conclusion:???? rtx4090 is 650% better

文章来源:https://blog.csdn.net/pkuyjxu/article/details/135058086
本文来自互联网用户投稿，该文观点仅代表作者本人，不代表本站立场。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。