Downloads · 30 days
0
asrval-mobile
felipe798/asrval-mobile
asrval-mobile is a automatic speech recognition model from felipe798. Use it when you need speech turned into text. It is set up for onnx. The card lists the license as cc-by-nc-4.0.
On-device Valencian ASR weights for the Parla app (GitHub FRojas1/asrVAL).
Access
Public
Updated Sep 26, 2026
Repo size
2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx1.8 GB · 91%
At a glance
- Task
- Automatic Speech Recognition
- Library
- onnx
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- Sep 8, 2026
- Updated
- Sep 26, 2026
- SHA
- 0b0e717c
Model card
From the Hugging Face model README
asrval-mobile
On-device Valencian ASR weights for the Parla app (GitHub FRojas1/asrVAL).
- Acoustic: Parakeet CTC 0.6B round-2, dynamic int8 ONNX (\model.int8.onnx)
- LM: token 3-gram v2 (gram.bin), alpha 0.5, beta 2.0, beam 16
- VAD: Silero (\silero_vad.onnx)
- Author (training): FRojas1
- Licence: CC-BY-NC-4.0 (Corts Valencianes training data). Non-commercial use only.
The Flutter app downloads these files on first launch. Do not bundle them in the IPA.
- Task
- Automatic Speech Recognition
- Library
- onnx
- License
- cc-by-nc-4.0
- Languages
- ca
- Created
- Sep 8, 2026
- Updated
- Sep 26, 2026