Aan de slagGa gratis aan de slag

Transcribing a non-English language

OpenAI's audio models can not only transcribe English speech but also perform well in speech in many other languages.

In this exercise, you'll create a transcript from audio.m4a, which contains speech in Portuguese.

Deze oefening maakt deel uit van de cursus

Multi-Modal Systems with the OpenAI API

Cursus bekijken

Oefeninstructies

  • Open the audio.m4a file in read-binary mode.
  • Create a transcription request to the Audio endpoint.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

client = OpenAI(api_key="")

# Open the audio.m4a file
audio_file = ____("____", "____")

# Create a transcript from the audio file
response = client.audio.transcriptions.____(model="whisper-1", file=____)

print(response.text)
Code bewerken en uitvoeren