Downloads · 30 days
0
whisper-hindi2hinglish-apex-ggml
voquill/whisper-hindi2hinglish-apex-ggml
whisper-hindi2hinglish-apex-ggml is a machine learning model from voquill. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
GGML-format conversion of Oriserve/Whisper-Hindi2Hinglish-Apex for use with whisper.cpp and downstream runtimes (e.g. whisper-rs).
Access
Public
Updated Apr 14, 2026
Repo size
624 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin624 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Apr 14, 2026
- Updated
- Apr 14, 2026
- SHA
- c088f27b
Base models
Model card
From the Hugging Face model README
Whisper-Hindi2Hinglish-Apex — GGML / whisper.cpp
GGML-format conversion of Oriserve/Whisper-Hindi2Hinglish-Apex for use with whisper.cpp and downstream runtimes (e.g. whisper-rs).
Transcribes Hindi audio into Hinglish (Hindi written in Latin script). Based on whisper-large-v3-turbo.
Files
| File | Size | Quantization |
|---|---|---|
ggml-hindi2hinglish-apex-q5_1.bin | ~595 MB | q5_1 |
Conversion
Produced with whisper.cpp/models/convert-h5-to-ggml.py (with a BFloat16 → float32 patch at the .numpy() call) followed by whisper-quantize ... q5_1.
License
Inherits from the base model (Oriserve/Whisper-Hindi2Hinglish-Apex).
- License
- apache-2.0
- Languages
- hi, en
- Created
- Apr 14, 2026
- Updated
- Apr 14, 2026