Downloads · 30 days
0
medocr-asr-bn
MrJAJA/medocr-asr-bn
medocr-asr-bn is a automatic speech recognition model from MrJAJA. Use it when you need speech turned into text. The card lists the license as mit.
INT8 (MatMul-only dynamic quantization) ONNX export of the encoder of ai4bharat/indicconformersttbnhybridctcrnntlarge (MIT license, AI4Bharat), plus its CTC head, vocabulary, and mel filterbank. MatMul-only quantizati…
Access
Public
Updated Jul 18, 2026
Repo size
197 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx197 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- License
- mit
- Access
- Public
- Created
- Jul 18, 2026
- Updated
- Jul 18, 2026
- SHA
- 4d66c7de
Model card
From the Hugging Face model README
medocr-asr-bn — on-device Bangla ASR (ONNX) for the MedOCR pharmacy app
INT8 (MatMul-only dynamic quantization) ONNX export of the encoder of ai4bharat/indicconformer_stt_bn_hybrid_ctc_rnnt_large (MIT license, AI4Bharat), plus its CTC head, vocabulary, and mel filterbank. MatMul-only quantization is used because onnxruntime-android has no ConvInteger kernel.
Used by the MedOCR Android app for offline voice stocking (the pharmacist
speaks price / expiry / quantity). The app downloads asr_encoder_bn.onnx
once on first use; the small files ship inside the APK.
| file | bytes |
|---|---|
| asr_encoder_bn.onnx | 185341627 |
| asr_ctc_bn.onnx | 11559655 |
| asr_vocab_bn.json | 57466 |
| asr_mel_filters.bin | 82240 |
Contract: encoder audio_signal [1,80,T] float32 + length [1] int64 →
[1,512,T']; ctc → logprobs [1,T',5633]; aggregate SentencePiece vocab,
blank id 5632; 16 kHz mono input.
- Task
- Automatic Speech Recognition
- License
- mit
- Languages
- bn
- Created
- Jul 18, 2026
- Updated
- Jul 18, 2026