• Original Model Card

Send Request

curl <AZUREML_ENDPOINT_URL> \
    -X POST \
    -H "Authorization: Bearer <AZUREML_TOKEN>" \
    -H "Content-Type: multipart/form-data" \
    -F file=@/path/to/file/audio.mp3 \
    -F model=nvidia/parakeet-ctc-1.1b

Supported Parameters

• file (file): The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
• model (string): ID of the deployed model as in the Hugging Face Hub.
• language (string, optional): The language of the input audio (ISO-639-1 code, e.g., "en"). Supplying this improves accuracy and latency.
• prompt (string, optional): An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.
• temperature (float, optional): Defaults to 0.
  • The sampling temperature, between 0 and 1. Higher values (e.g., 0.8) make output more random; lower values (e.g., 0.2) make it more focused and deterministic.
  • If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.
• response_format (string, optional): Defaults to json.
  • The format of the output: json, text, srt, verbose_json, or vtt.