Downloads · 30 days
0
high-vibes-models
LiamDeacon/high-vibes-models
high-vibes-models is a automatic speech recognition model from LiamDeacon. Use it when you need speech turned into text. The card lists the license as other.
This repository hosts voice model artifacts for the High Vibes app. The primary target is on-device speech-to-text with a mobile-friendly download size.
Access
Public
Updated Dec 30, 2025
Repo size
896 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.data444 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- License
- other
- Access
- Public
- Created
- Dec 27, 2025
- Updated
- Dec 30, 2025
- SHA
- 44378eb5
Model card
From the Hugging Face model README
High Vibes Voice Models
This repository hosts voice model artifacts for the High Vibes app. The primary target is on-device speech-to-text with a mobile-friendly download size.
Included Artifacts
Parakeet CTC 0.6B (Quantized)
- Model ID:
parakeet-ctc-0.6b-quant - Format: ONNX with external data
- Quantization: MatMulNBits int4 + fp16 conversion for remaining weights
- Intended usage: mobile speech-to-text (offline)
Source Model
The quantized artifact is derived from nvidia/parakeet-ctc-0.6b via
NVIDIA NeMo export tooling and ONNX Runtime quantization.
Manifests
Platform manifests live here:
manifests/ios.jsonmanifests/android.json
Notes
These artifacts are intended for use inside High Vibes. They are not provided as training checkpoints.
- Task
- Automatic Speech Recognition
- License
- other
- Languages
- en
- Created
- Dec 27, 2025
- Updated
- Dec 30, 2025