🍎📱🎙️ Shenava Koochik 1.0 — Core ML streaming for iOS 15
Cache-aware FP16 Core ML NeuralNetwork export for Apple devices that cannot use the newer ML Program package. It uses Core ML specification version 5, has iOS 14/macOS 11 availability, and is designed to compile and run on iOS 15.
✨ At a glance | معرفی سریع
| English | فارسی | |
|---|---|---|
| 📱 Role | Streaming ASR for older Apple devices | تشخیص گفتار جریانی برای دستگاههای قدیمیتر اپل |
| 📦 Format | FP16 Core ML NeuralNetwork | NeuralNetwork با وزنهای FP16 |
| ⏱️ Step | One prediction per 170 ms | یک پیشبینی در هر ۱۷۰ میلیثانیه |
| 🧠 State | Cache-aware; caches cross calls | cacheها بین فراخوانیها منتقل میشوند |
| 🎯 Target | iOS 15; spec supports iOS 14/macOS 11 | هدف iOS 15 با سازگاری spec قدیمیتر |
- Canonical repository:
Reza2kn/Shenava-Koochik-1.0-CoreML-iOS15-fp16 - PersianML mirror:
PersianML/Shenava-Koochik-1.0-CoreML-iOS15-fp16 - Parent:
Reza2kn/Shenava-Koochik-v1.0
🌊 Streaming contract
Each call produces one CTC step from a 170 ms feature window and returns the caches for the next call.
Inputs:
processed_signal: FP32[1, 80, 17]cache_last_channel: FP32[17, 1, 70, 512]cache_last_time: FP32[17, 1, 512, 8]
Outputs:
logits: FP32[1, 1, 1025]cache_last_channel_next: FP32[17, 1, 70, 512]cache_last_time_next: FP32[17, 1, 512, 8]
The graph uses 9 frames of pre-encode cache plus an 8-frame chunk, 17 conformer layers, and a constant channel-cache length of 70. Initialize both caches to zero and thread each *_next output into the next call.
📦 Files
*_ios15_fp16.mlmodel: 212 MB NeuralNetwork model.*_manifest.json: authoritative streaming shapes and export provenance.tokens.json,mel_filters_slaney_80x257.json,preprocessor.json: tokenizer/feature assets.export_koochik10_streaming_coreml.py: reproducible exporter.
For the streaming graph, treat shenava_koochik_1_0_ctc_streaming_att70_0_ios15_fp16_manifest.json and the export script as authoritative. The fixed-window fields retained in preprocessor.json describe the shared feature pipeline, not this graph’s 17-frame tensor contract.
Published FP16-versus-FP32 argmax agreement: 1.000.
🛠️ Compile for iOS 15
xcrun coremlcompiler compile \
shenava_koochik_1_0_ctc_streaming_att70_0_ios15_fp16.mlmodel \
./CompiledModels \
--deployment-target 15.0 \
--platform ios
🇮🇷 خلاصهٔ فارسی
این نسخه برای اجرای جریانی روی iOS 15 و دستگاههای قدیمیتر اپل ساخته شده است. در هر فراخوانی ۱۷۰ میلیثانیه پردازش میشود و cacheهای خروجی باید به فراخوانی بعدی داده شوند. قرارداد دقیق tensorها در فایل manifest قرار دارد.
🌌 Explore Shenava-1
🧠 Koochik source · 🍎 Modern fixed-window Core ML · 📱 iOS 15 streaming · 🌐 Browser ONNX · 🦀 Rust streaming
Apache-2.0. Output numbers are spoken-form Persian unless the host applies ITN.
- Downloads last month
- -
Model tree for PersianML/Shenava-Koochik-1.0-CoreML-iOS15-fp16
Base model
nvidia/stt_fa_fastconformer_hybrid_large