Automatic Speech Recognition
Transformers
NeMo
Safetensors
PyTorch
parakeet_tdt
feature-extraction
speech
audio
Transducer
Transformer
TDT
FastConformer
Conformer
NeMo
hf-asr-leaderboard
Transformers
Eval Results (legacy)
Eval Results
Instructions to use nvidia/parakeet-tdt-0.6b-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/parakeet-tdt-0.6b-v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nvidia/parakeet-tdt-0.6b-v3")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/parakeet-tdt-0.6b-v3", dtype="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Environment setup
#35
by pr-tet-usr - opened
This is a great model and I was trying to finetune it for my specific use case, but somehow every run ends up in the same wheel- box
RuntimeError: CUDA driver error: operation not supported
Have tried various package version setups and nemo library setups, none of them seem to work.
Myself I have now Python 3.11.14 and Cuda version 13.0.
Can anyone provide suggestions for the setup that would allow to run the model train or maybe their package versions?
Hi,
I've recently replicated my Conda environment for finetuning Parakeet. These versions and packages worked well for me
- conda create -n nemo-ft python=3.12.9
- conda activate nemo-ft
- conda install pip
- pip install torch==2.6.0+cu118 torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
- pip install transformers==4.51.3 librosa==0.11.0
- pip install "nemo_toolkit[asr]==2.4.1"
Hope that helps! Regards