Downloads · 30 days
0
betterflow-whisper-hindi-medium-q4_0
mobilebytesensei/betterflow-whisper-hindi-medium-q4_0
betterflow-whisper-hindi-medium-q4_0 is a machine learning model from mobilebytesensei. 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.
On-device Hindi ASR model for the betterflow keyboard (privacy-first, India-first, on-device dictation). This is vasista22/whisper-hindi-medium (a Whisper-medium fine-tune for Hindi, Apache-2.0) quantized to q40 ggml…
Access
Public
Updated Jul 9, 2026
Repo size
444 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin444 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jul 9, 2026
- Updated
- Jul 9, 2026
- SHA
- c00c946d
Model card
From the Hugging Face model README
betterflow — whisper-hindi-medium q4_0 (ggml)
On-device Hindi ASR model for the betterflow keyboard (privacy-first, India-first, on-device
dictation). This is vasista22/whisper-hindi-medium
(a Whisper-medium fine-tune for Hindi, Apache-2.0) quantized to q4_0 ggml via whisper.cpp for
on-device inference. Single self-contained file, ~424 MB.
Validation (betterflow GATE-0 Phase B)
Keeps the Indic accuracy wedge at a phone-viable size — FLEURS-Hindi 8.2% WER, Common Voice-Hindi
21.7% WER, vs generic whisper-large-v3-turbo 28.5% / 39.7% on the same clips.
Usage
Load with whisper.cpp: whisper_init_from_file(...).
- Base:
vasista22/whisper-hindi-medium(fine-tune ofopenai/whisper-medium) - Quantization: whisper.cpp
q4_0 - Runtime: whisper.cpp (ggml)
- sha256:
695119b8bae27c3ec341ff01c8c8e2f5071766aa4ec4803fe7076aa49cddd6d5
- License
- apache-2.0
- Languages
- hi
- Created
- Jul 9, 2026
- Updated
- Jul 9, 2026