Downloads · 30 days
7
21% of all-time downloads
whisper-tiny-static-shape-quantized-SL-448
mohitsha/whisper-tiny-static-shape-quantized-SL-448
whisper-tiny-static-shape-quantized-SL-448 is a automatic speech recognition model from mohitsha. Use it when you need speech turned into text. It is set up for transformers.
The repository contains the whisper model quantized using the Smooth Quant using ONNXRuntime
All-time downloads
33
Public
Repo size
499 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx499 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- whisper
- Access
- Public
- Created
- Oct 6, 2023
- Updated
- Oct 24, 2023
- SHA
- d822bfb0
Model card
From the Hugging Face model README
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
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- Created
- Oct 6, 2023
- Updated
- Oct 24, 2023