> ## Documentation Index
> Fetch the complete documentation index at: https://docs.beam.cloud/llms.txt
> Use this file to discover all available pages before exploring further.

# Whisper Video Transcription

> Deploying Whisper as a REST API to transcribe YouTube videos

In this example, we'll build a simple app which transcribes YouTube videos using [Whisper](https://github.com/openai/whisper), a state-of-the-art model for speech recognition.

<div class="container" style={{}}>
  <form action="https://github.com/slai-labs/get-beam/tree/main/examples/whisper" method="get" target="_blank">
    <button
      class="button"
      type="submit"
      style={{
    margin: "auto",
    width: 250,
    borderRadius: 5,
    color: "rgb(237, 238, 240)",
    backgroundColor: "rgb(71, 127, 247)",
    fontWeight: "bold",
    boxShadow: "0 0 3px 2px #cec7c759",
  }}
    >
      Try this example on Github
    </button>
  </form>
</div>

### Setting up the environment

First, you'll setup your compute environment. You'll specify:

* Compute requirements, including a GPU
* Python and system-level packages to install in the runtime

```python app.py theme={null}
app = App(
    name="whisper-example",
    runtime=Runtime(
        cpu=2,
        memory="16Gi",
        gpu="A10G",
        image=Image(
            python_version="python3.8",
            python_packages=[
                "git+https://github.com/openai/whisper.git",
                "pytube @ git+https://github.com/felipeucelli/pytube@03d72641191ced9d92f31f94f38cfb18c76cfb05",
            ],
            commands=["apt-get update && apt-get install -y ffmpeg"],
        ),
    ),
)
```

### Transcribing YouTube Videos

We'll write a basic function which takes in a YouTube video URL, uses the [youtube\_dl](https://github.com/ytdl-org/youtube-dl) library to download the video as an [Output](/v2/data/output), and runs the video through Whisper to generate a text transcript.

<Accordion title="Show Code">
  ```python run.py theme={null}
  import whisper
  import youtube_dl


  def transcribe(**inputs):
      # Grab the video URL passed from the API
      video_url = inputs["video_url"]

      # Create YouTube object
      yt = YouTube(video_url)
      video = yt.streams.filter(only_audio=True).first()

      # Download audio to the output path
      out_file = video.download(output_path="./")
      base, ext = os.path.splitext(out_file)
      new_file = base + ".mp3"
      os.rename(out_file, new_file)
      a = new_file

      # Load Whisper and transcribe audio
      model = whisper.load_model("small")
      result = model.transcribe(a)

      print(result["text"])
      return {"pred": result["text"]}


  if __name__ == "__main__":
      video_url = "https://www.youtube.com/watch?v=adJFT6_j9Uk&ab_channel=minutephysics"
      transcribe(video_url=video_url)
  ```
</Accordion>

### Deployment

You'll deploy the app by entering your shell, and running:

```sh theme={null}
beam deploy app.py
```

Your Beam Dashboard will open in a browser window, and you can monitor the deployment status in the web GUI.

### Calling the API

You'll call the API by pasting in the cURL command displayed in the browser window.

```sh theme={null}
  curl -X POST --compressed "https://apps.beam.cloud/77n0o" \
   -H 'Authorization: [YOUR_AUTH_TOKEN]' \
   -H 'Content-Type: application/json' \
   -d '{"video_url": "https://www.youtube.com/watch?v=adJFT6_j9Uk"}'
```

The API will return a transcript with our video:

```json theme={null}
{
  "pred": " Welcome to the Pets Show. That is, Physics Explained in 10 Seconds. For the next month, in addition to Minute Physics, I'll be making one 10-second video every day. 10 Seconds of Physics explaining 5 seconds of titles on either end."
}
```