Downloads · 30 days
12
8% of all-time downloads
MachinesFluent/parakeet-v3-tdt-f32-crispasr-gguf
parakeet-v3-tdt-f32-crispasr-gguf is a automatic speech recognition model from MachinesFluent. Use it when you need speech turned into text. The card lists the license as cc-by-4.0.
This repository contains a full-precision F32 GGUF version of NVIDIA Parakeet TDT 0.6B v3, prepared for direct use with CrispASR.
Downloads · 30 days
12
8% of all-time downloads
All-time downloads
146
Public
Repo size
2.5 GB
Likes
0
Public
Click a slice to open those files.
.gguf2.5 GB · 100%
From the Hugging Face model README
This repository contains a full-precision F32 GGUF version of NVIDIA Parakeet TDT 0.6B v3, prepared for direct use with CrispASR.
It was created for MachinesFluent, a Windows desktop dictation application, but the model can also be used by other compatible CrispASR applications.
The original F32 model weights remain unchanged. The GGUF container was repackaged to match the format expected by CrispASR, including the required Parakeet preprocessing data.
File:
parakeet-v3-full-precision-f32.gguf
Size:
2,508,622,944 bytes
SHA-256:
bfa76fccffede7a76a0d975f0e3c6778168f6a7fbde36add035b5ef74236fbf8
This package has been prepared and tested with CrispASR 0.8.25.1 and the MachinesFluent Parakeet processor.
The CrispASR runtime is not included in this repository.
The original Parakeet model and weights were created by the NVIDIA NeMo team and are distributed under the Creative Commons Attribution 4.0 license.
This repository provides a runtime-compatible format adaptation. It does not claim ownership of the original model or research.