Views
No views yet
| 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 |
Reza2kn/Shenava-Koochik-1.0-CoreML-iOS15-fp16PersianML/Shenava-Koochik-1.0-CoreML-iOS15-fp16Reza2kn/Shenava-Koochik-v1.0processed_signal: FP32 [1, 80, 17]cache_last_channel: FP32 [17, 1, 70, 512]cache_last_time: FP32 [17, 1, 512, 8]logits: FP32 [1, 1, 1025]cache_last_channel_next: FP32 [17, 1, 70, 512]cache_last_time_next: FP32 [17, 1, 512, 8]*_next output into the next call.*_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.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.1xcrun coremlcompiler compile \
2 shenava_koochik_1_0_ctc_streaming_att70_0_ios15_fp16.mlmodel \
3 ./CompiledModels \
4 --deployment-target 15.0 \
5 --platform ios