# Widget faster than inference Api?

**URL:** <https://discuss.huggingface.co/t/widget-faster-than-inference-api/11755>\
**Category:** Models\
**Created:** [November 15, 2021, 2:24pm UTC](https://discuss.huggingface.co/t/widget-faster-than-inference-api/11755 "2021-11-15T14:24:26Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![amtam0](https://avatars.discourse-cdn.com/v4/letter/a/a88e4f/32.png) [@amtam0](https://discuss.huggingface.co/u/amtam0)\
**Post date:** [November 15, 2021, 2:24pm UTC](https://discuss.huggingface.co/t/widget-faster-than-inference-api/11755/1 "2021-11-15T14:24:26Z")

</div>

Hello,

I am getting some process time difference between widget (not cached) and inference Api between 1 to 2 seconds, when testing the same .wav file.

The model I tested : speechbrain/asr-wav2vec2-commonvoice-fr. I checked this model does not support accelerated inference.

I am wondering if this is a normal behavior?

## To reproduce

Use the same wav file to test the model using

1. The widget : [speechbrain/asr-wav2vec2-commonvoice-fr · Hugging Face](https://huggingface.co/speechbrain/asr-wav2vec2-commonvoice-fr) (not the cached file)
2. The inference Api, code sample used :

```auto
%%time
import json
import requests
API_TOKEN = ""
model_id = "speechbrain/asr-wav2vec2-commonvoice-fr"
headers = {"Authorization": f"Bearer {API_TOKEN}"}
API_URL = "https://api-inference.huggingface.co/models/{}".format(model_id)
def query(filename, API_URL, headers):
    with open(filename, "rb") as f:
        data = f.read()
    response = requests.request("POST", API_URL, headers=headers, data=data)
    return json.loads(response.content.decode("utf-8"))
data = query("example2.wav", API_URL, headers)

```

## Expected behavior

Similar process time