Downloads · 30 days
9
17% of all-time downloads
parakeet-tdt-0.6b-v3
slyusarev/parakeet-tdt-0.6b-v3
parakeet-tdt-0.6b-v3 is a automatic speech recognition model from slyusarev. Use it when you need speech turned into text. The card lists the license as cc-by-4.0.
nvidia/parakeet-tdt-0.6b-v3 exported to ONNX and quantized to int8. Built for Textolit, an offline dictation app — the app downloads these files automatically.
All-time downloads
53
Public
Repo size
672 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx672 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- License
- cc-by-4.0
- Model type
- nemo-conformer-tdt
- Access
- Public
- Created
- Aug 28, 2026
- Updated
- Aug 28, 2026
- SHA
- 780790e3
Base models
Model card
From the Hugging Face model README
Parakeet TDT 0.6B v3 — ONNX (int8)
nvidia/parakeet-tdt-0.6b-v3 exported to ONNX and quantized to int8. Built for Textolit, an offline dictation app — the app downloads these files automatically.
| File | Size | SHA-256 |
|---|---|---|
encoder-model.int8.onnx | 654 MB | 7897d54aa72b4f280c816dc59d296ee3f6436180b69088fba0c57806ea6d840d |
decoder_joint-model.int8.onnx | 18 MB | 05892ef89093e7dabcf23b83b4123089ff00231f6556b1b67f4350eaf454b5e5 |
vocab.txt | 94 KB | d58544679ea4bc6ac563d1f545eb7d474bd6cfa467f0a6e2c1dc1c7d37e3c35d |
config.json | 98 B | 21565538716b1cb134a096e3df9fa3f27f0470bc09c596d9faa578dc27d945d5 |
The audio preprocessor is not included: Textolit computes mel features itself.
License: CC-BY-4.0, inherited from the original. Attribution: NVIDIA; the export to ONNX and the int8 quantization named above are the only changes to their model — nothing was retrained.
- Task
- Automatic Speech Recognition
- Type
- nemo-conformer-tdt
- License
- cc-by-4.0
- Languages
- ru, en, bg, hr, cs, da
- Created
- Aug 28, 2026
- Updated
- Aug 28, 2026