plug.directory
Add my server

Whisper Large V3

by hf-audioco.huggingface.hf-audio/whisper-large-v3

  • Remote endpoint
  • 3 tools
  • whisper_large_v3_transcribe Transcribe or translate an audio input using the Whisper Large V3 model. This function runs automatic speech recognition on an uploaded or recorded audio file using a Hugging Face Transformers pipeline. It supports both transcription (same-language) and translation (to English). If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: str: The transcribed or translated text output from the Whisper model.
  • whisper_large_v3_transcribe_1 Transcribe or translate an audio input using the Whisper Large V3 model. This function runs automatic speech recognition on an uploaded or recorded audio file using a Hugging Face Transformers pipeline. It supports both transcription (same-language) and translation (to English). If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: str: The transcribed or translated text output from the Whisper model.
  • whisper_large_v3_yt_transcribe Transcribe or translate audio from a YouTube video. This function downloads a YouTube video, extracts its audio, converts it to the appropriate format, and runs Whisper-based automatic speech recognition on the content. Returns: tuple:, - html_embed_str (str): An HTML iframe embedding the YouTube video., - text (str): The transcribed or translated text output.

As the server's own listing gives them. We never call a tool.