Instructions to use mohitsha/whisper-tiny-static-shape-quantized-SL-448 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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")# pip install -U transformers accelerate # 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", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from mohitsha/whisper-tiny-static-shape-quantized-SL-448: direct link, hf CLI and curl.
- Browser
- Download file 562 Bytes
-
https://huggingface.co/mohitsha/whisper-tiny-static-shape-quantized-SL-448/resolve/main/README.md
- Command line
-
hf download hf://mohitsha/whisper-tiny-static-shape-quantized-SL-448/README.md
-
curl -L -o README.md https://huggingface.co/mohitsha/whisper-tiny-static-shape-quantized-SL-448/resolve/main/README.md
562 Bytes
Whisper Model Quantized
The repository contains the whisper model quantized using the Smooth Quant using ONNXRuntime
- Only the Whisper decoder is quantized in the model
- The model has been modified to accept fixed shapes input of (1, 80, 3000) for the encoder and (1,448) for decoder.
- For inference the un-quantized encoder model and quantized decoder model is used.
- This model is for testing and could be modified in the future with better versions.
Evaluation:
The model achieves WER of 6.02% on the librispeech_asr (clean) test dataset