# Build pretrained huggingface whisper for tensorrt-llm

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbuild-pretrained-huggingface-whisper-for-tensorrt-llm%2F87475%3E%5C
**Category:** Intermediate\
**Created:** [May 20, 2024, 7:40am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbuild-pretrained-huggingface-whisper-for-tensorrt-llm%2F87475 "2024-05-20T07:40:31Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![sangyoonlee](https://avatars.discourse-cdn.com/v4/letter/s/8797f3/32.png) [@sangyoonlee](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsangyoonlee)%5C
**Post date:** [May 20, 2024, 7:40am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbuild-pretrained-huggingface-whisper-for-tensorrt-llm%2F87475%2F1 "2024-05-20T07:40:31Z")

</div>

I have pretrained whisper-large-v2 model with my custom dataset, and tried to build tensorrt-llm.  
But I got `[Errno 2] No such file or directory: '/workspace/models/whisper-large-v2/large-v2.pt'`, even though given model dir has no .pt file. So I took this error log as “tensorrt-llm handles only .pt file like whisper official model.”  
So my question is, how to convert huggingface .bin weight file to whisper’s .pt, including layer name?