parakeet-tdt-0.6b-v2 (HuggingFace format)

Unofficial HF-format conversion of nvidia/parakeet-tdt-0.6b-v2 for use with transformers >= 5.8.dev (AutoModelForTDT).

Upstream only ships the .nemo bundle, and transformers' own convert_nemo_to_hf.py script doesn't handle v2's 1024-token vocab (it hardcodes a labels.index("<pad>") assumption that only holds for v3). This repo is the conversion output with that one-line fallback applied — see live-llm-bench/scripts/convert-parakeet-v2-nemo-to-hf.py for the exact transform. Weights are identical to upstream; only the packaging is changed.

Usage

from transformers import AutoModelForTDT, AutoProcessor

model_id = "ai-and-i-project/parakeet-tdt-0.6b-v2-hf"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForTDT.from_pretrained(model_id, dtype="auto", device_map="cuda")

License

Inherits cc-by-4.0 from nvidia/parakeet-tdt-0.6b-v2.

Downloads last month
21
Safetensors
Model size
0.6B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ai-and-i-project/parakeet-tdt-0.6b-v2-hf

Finetuned
(40)
this model