Featured Community Checkpoints

Community fine-tunes built on NVIDIA NeMo ASR checkpoints and published on Hugging Face. For NVIDIA-published checkpoints, see ASR Model Checkpoints and the NVIDIA Hugging Face organization.

Note

Community checkpoints are maintained by their authors, not by the NeMo team. Use each model’s Hugging Face model card and the framework project linked below for up-to-date setup and inference instructions.

Checkpoint	What’s special	Framework
akera/parakeet-tdt-salt	SALT multilingual ASR for 10 East African languages. Hybrid TDT+CTC FastConformer (600M), fine-tuned from parakeet-tdt-0.6b-v3.	NeMo
johannhartmann/parakeet_de_med	German medical documentation ASR (PEFT). WER 11.73% → 3.28% on a 122-sample medical eval set.	NeMo
qenneth/parakeet-tdt-0.6b-v3-finetuned-for-ATC	ATC English ASR on jacktol/ATC-ASR-Dataset. Test WER 5.99%.	NeMo
KasuleTrevor/parakeet-0.6b-cv-sw-5hr_v9	Swahili ASR fine-tune on ~5 hours of Common Voice data.	NeMo
NeurologyAI/neuro-parakeet-mlx	German medical/neurology ASR for Apple Silicon. WER 1.04% on the author’s medical validation set.	MLX
cstr/parakeet-tdt-0.6b-v3-GGUF	Quantised Parakeet TDT (Q4_K ~467 MB). 25 EU languages, word-level timestamps.	GGUF (CrispASR)
cstr/canary-1b-v2-GGUF	Quantised Canary 1B (Q4_K ~673 MB). Multilingual ASR and speech translation.	GGUF (CrispASR)

Submit a Community Checkpoint

To suggest a checkpoint for this page, open a GitHub issue with the Hugging Face model link, NeMo base checkpoint, task, languages, evaluation results, and inference framework.