Downloads · 30 days
0
parakeet-tdt-0.6b-v3
maxkulish/parakeet-tdt-0.6b-v3
parakeet-tdt-0.6b-v3 is a automatic speech recognition model from maxkulish. Use it when you need speech turned into text. The card lists the license as cc-by-4.0.
ONNX-exported version of NVIDIA's Parakeet TDT 0.6B v3 automatic speech recognition model, for use with parakeet-rs and ONNX Runtime.
Access
Public
Updated Feb 18, 2026
Repo size
2.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.data2.4 GB · 96%
At a glance
- Task
- Automatic Speech Recognition
- License
- cc-by-4.0
- Access
- Public
- Created
- Feb 18, 2026
- Updated
- Feb 18, 2026
- SHA
- 17793985
Model card
From the Hugging Face model README
Parakeet TDT 0.6B v3 (ONNX)
ONNX-exported version of NVIDIA's Parakeet TDT 0.6B v3 automatic speech recognition model, for use with parakeet-rs and ONNX Runtime.
Attribution
This model is a mirror of ONNX-exported weights originally created by altunenes/parakeet-rs, derived from NVIDIA's parakeet-tdt-0.6b-v3.
Files
| File | Size | SHA256 |
|---|---|---|
encoder-model.onnx | 40 MB | 98a74b21b4cc0017c1e7030319a4a96f4a9506e50f0708f3a516d02a77c96bb1 |
encoder-model.onnx.data | 2.3 GB | 9a22d372c51455c34f13405da2520baefb7125bd16981397561423ed32d24f36 |
decoder_joint-model.onnx | 69 MB | e978ddf6688527182c10fde2eb4b83068421648985ef23f7a86be732be8706c1 |
vocab.txt | 92 KB | d58544679ea4bc6ac563d1f545eb7d474bd6cfa467f0a6e2c1dc1c7d37e3c35d |
Usage
Used by rs-wisper for local offline speech-to-text transcription via the parakeet-rs crate.
- Task
- Automatic Speech Recognition
- License
- cc-by-4.0
- Languages
- en
- Created
- Feb 18, 2026
- Updated
- Feb 18, 2026