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", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
training script
#17
by sugintama - opened
In the example training script, the parameters are lr=0.001, betas=[0.9,0.999], weight_decay=0.0001. But in the released NeMo file, they are lr=1.0e-05, betas=[0.9,0.98], weight_decay=0.001, sched:=CosineAnnealing. Which set should I use?
We trained this model in two stages as mentioned here: https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3#training
First stage: Trained for 150000 steps usinglr=0.001 with CosineAnnealing scheduler and warmup of 15000
Second stage: Trained for 5000 steps usinglr=1e-5 with CosineAnnealing scheduler and warmup of 0