Downloads · 30 days
19
9% of all-time downloads
smcleod/parakeet-tdt-0.6b-v2-int8
parakeet-tdt-0.6b-v2-int8 is a automatic speech recognition model from smcleod. Use it when you need speech turned into text. The card lists the license as cc-by-2.0.
I converted and quantised this from NVIDIA Parakeet TDT 0.6B V2 (En) as I found https://huggingface.co/istupakov/parakeet-tdt-0.6b-v2-onnx caused errors in text such as unintended word concatenation.
Downloads · 30 days
19
9% of all-time downloads
All-time downloads
209
Public
Repo size
2.3 GB
Likes
3
Public
Click a slice to open those files.
.onnx661 MB · 58%
From the Hugging Face model README
I converted and quantised this from NVIDIA Parakeet TDT 0.6B V2 (En) as I found https://huggingface.co/istupakov/parakeet-tdt-0.6b-v2-onnx caused errors in text such as unintended word concatenation.
If you need to reconvert from source, I've created a few helper scripts and included them in in conversion_scripts/.
cd conversion_scripts
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
PyTorch 2.5 is required as newer versions have breaking changes in the ONNX export API.
The scripts automatically download the source model if not present. Output files go to ./output/.
# Build the mel-spectrogram preprocessor
python build_preprocessor.py
# Export and quantise to int8 (dynamic quantisation - fast)
python export_model.py
# Or use static quantisation with calibration data (better quality)
python export_model.py --quantise=static
# Or export fp32 only (no quantisation)
python export_model.py --no-quantise
Dynamic quantisation (default): Fast, no calibration data needed. Weights are quantised at export time, activations are quantised at runtime. Good balance of speed and quality.
Static quantisation (--quantise=static): Uses 200 LibriSpeech samples to calibrate activation ranges. Both weights and activations are quantised with fixed scales. May provide better accuracy for some use cases but takes longer to export.
Static quantisation outputs to ./output/static/ and includes an external data file (encoder-model.int8.onnx.data) due to the model size.
encoder-model.int8.onnx - Encoder (~622MB dynamic, ~42MB + ~581MB external data for static)decoder_joint-model.int8.onnx - Decoder + joiner (8.6MB)nemo128.onnx - Mel-spectrogram preprocessor (137KB)vocab.txt - Token vocabularyconfig.json - Model configurationparakeet-tdt-0.6b-v2-int8.tar.gz - Archive of all model files