Downloads · 30 days
0
voice-sage95m-fp16
krut42/voice-sage95m-fp16
voice-sage95m-fp16 is a machine learning model from krut42. 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 mit.
FP16 ONNX export of ai-forever/sage-fredt5-distilled-95m (SAGE Russian spelling correction, FRED-T5 distilled 95M) for on-device transcript polishing in the «Диктофон» voice-recorder app.
Access
Public
Updated Jul 7, 2026
Repo size
260 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx260 MB · 99%
At a glance
- License
- mit
- Access
- Public
- Created
- Jul 7, 2026
- Updated
- Jul 7, 2026
- SHA
- 3b0170d9
Base models
Model card
From the Hugging Face model README
voice-sage95m-fp16
FP16 ONNX export of ai-forever/sage-fredt5-distilled-95m (SAGE Russian spelling correction, FRED-T5 distilled 95M) for on-device transcript polishing in the «Диктофон» voice-recorder app.
Replaces the earlier int8 export: ONNX Runtime's int8 MatMulInteger kernel
crashes natively (SIGILL/SIGSEGV) at inference on some ARM phone CPUs
(i8mm/dotprod path). FP16 uses ordinary MatMul kernels that don't depend on
those instructions, at ~2x the int8 size but a fraction of fp32.
Files (encoder + no-KV-cache decoder, matching the app's greedy decode loop):
encoder_model.onnx(~98 MB)decoder_model.onnx(~162 MB, no KV cache)vocab.json,merges.txt- GPT-2 byte-level BPE (FRED-T5), unchanged.
Special tokens: BOS <LM>=50357, EOS </s>=2, decoder start <pad>=0.
License: MIT (inherited from the base model).
- License
- mit
- Languages
- ru
- Created
- Jul 7, 2026
- Updated
- Jul 7, 2026