# CUDA not working with asr pipeline

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcuda-not-working-with-asr-pipeline%2F79972%3E%5C
**Category:** 🤗Transformers\
**Created:** [April 3, 2024, 11:36am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcuda-not-working-with-asr-pipeline%2F79972 "2024-04-03T11:36:32Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![tyrion8tyrion](https://avatars.discourse-cdn.com/v4/letter/t/8e7dd6/32.png) [@tyrion8tyrion](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ftyrion8tyrion)%5C
**Post date:** [April 3, 2024, 11:36am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcuda-not-working-with-asr-pipeline%2F79972%2F1 "2024-04-03T11:36:32Z")

</div>

Hi,  
I want to use CUDA to run a pipeline on several one minute audios. It seems that the GPU ( NVIDIA GeForce RTX 3080) is recognising the model, which occupies 3.5 gb in memory as indicated in the task manager. But then when I check the GPU usage It remains at 1% and the temperature does not increase. I have no idea why this might occur.  
Below are the relevant packages that I am using and the code snippet:

- torch 2.2.1+cu118
- torchaudio 2.2.1+cu118
- cuda driver 11.8
- transformers 4.36.1

```auto
model_path = hf_downloader.download_model(modelo)
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model = WhisperForConditionalGeneration.from_pretrained(
        model_path,
        torch_dtype=torch_dtype,
        low_cpu_mem_usage=True,
        use_safetensors=True)
device = "cuda:0" if torch.cuda.is_available() else "cpu"
model.to(device)
feature_extractor = WhisperFeatureExtractor.from_pretrained(model_path)
tokenizer = WhisperTokenizer.from_pretrained(model_path, language="spanish", task="transcribe")

asr_pipe = pipeline(
            "automatic-speech-recognition",
            model=model,
            feature_extractor=feature_extractor,
            tokenizer=tokenizer,
            chunk_length_s=10,
            stride_length_s=(4, 2),
            batch_size=16,
            torch_dtype=torch_dtype,
            device=device,
        )
data = load_from_disk(datapath) #audio dataset with 3000 audios
arrays = [data['audio'][i]['array'] for i in range(len(data))]
res = asr_pipe(arrays, return_timestamps=True)

```

Has anyone experienced a similar issue when trying to run ASR pipeline with CUDA?