# No cuda support for asr pipeline

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fno-cuda-support-for-asr-pipeline%2F59280%3E%5C
**Category:** 🤗Transformers\
**Created:** [October 20, 2023, 1:39pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fno-cuda-support-for-asr-pipeline%2F59280 "2023-10-20T13:39:35Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![katilda](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/katilda/32/18632_2.png) [@katilda](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fkatilda)%5C
**Post date:** [October 20, 2023, 1:39pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fno-cuda-support-for-asr-pipeline%2F59280%2F1 "2023-10-20T13:39:35Z")

</div>

am i crazy or is it impossible to put inputs to cuda with asr pipeline?  
if i do:  
pipe = pipeline(‘automatic-speech-recognition’, device=‘cuda’)  
and then run:  
pipe(inputs = audio\_array.numpy())  
i get  
RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same  
i think the inputs are just never sent to the device in the code ([https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/pipelines/automatic\_speech\_recognition.py#L294](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/pipelines/automatic_speech_recognition.py#L294)) …