How to use mohitsha/whisper-tiny-static-shape-quantized-SL-448 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="mohitsha/whisper-tiny-static-shape-quantized-SL-448")
# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("mohitsha/whisper-tiny-static-shape-quantized-SL-448") model = AutoModelForSpeechSeq2Seq.from_pretrained("mohitsha/whisper-tiny-static-shape-quantized-SL-448")
Hi,Could you share how this model was created step by step? especially how the fixed lengths were set for the encoder and decoder and how you chose to generate onnx files with and without kv cache
· Sign up or log in to comment
