whisper

Model type	whisper
Class	WhisperForConditionalGeneration
Task	speech-to-text
Source	models/whisper.py

Description

Whisper encoder-decoder model for speech recognition and transcription.

This class holds both WhisperEncoderModel and WhisperDecoderModel as sub-modules. Use SpeechToTextTask.build() to trace them into separate ONNX models.

Usage

mobius build --model <MODEL_ID> output_dir/

from mobius import build

model = build("<MODEL_ID>")