Reza2kn/Shenava-Koochik-1.0-CoreML-iOS15-fp16

Shenava — Koochik 1.0 (114M) · CoreML iOS15 NeuralNetwork fp16

CoreML NeuralNetwork (not ML Program) fp16 export of Reza2kn/Shenava-Koochik-1.0 — built so older Apple devices capped at iOS 15 (e.g. iPad Air 2 / iOS 15.8) can load and run it. ML Program packages require iOS 16+; this targets NeuralNetwork / CoreML spec v5 with iOS 14 availability, so it runs on iOS 15.

This is the cache-aware streaming step (one 170 ms prediction), the same kind of artifact as shenava-fa-fastconformer-streaming-32m-coreml-ios15-fp16.

The Shenava-1 family (CoreML iOS15)

• Shenava-Koochik-1.0-CoreML-iOS15-fp16 — Koochik 1.0 (114M) · teacher / flagship
• Shenava-Rizeh-v1.0-CoreML-iOS15-fp16 — Rizeh v1.0 (32M) · mid-tier
• Shenava-Rizeh-Pizeh-v1.0-CoreML-iOS15-fp16 — Rizeh Pizeh v1.0 (6.9M) · tiniest

Benchmark — fair WER/CER (parent model, decoded @ [70,13])

Member	golden-6669 WER	CER	FLEURS-fa WER	CER
Koochik 1.0 (114M)	7.49%	2.30%	10.64%	3.79%

CoreML contract (cache-aware streaming CTC step, att_context [70,0])

Inputs:

• processed_signal: Float32 [1, 80, 17]
• cache_last_channel: Float32 [17, 1, 70, 512]
• cache_last_time: Float32 [17, 1, 512, 8]

Outputs:

• logits: Float32 [1, 1, 1025]
• cache_last_channel_next: Float32 [17, 1, 70, 512]
• cache_last_time_next: Float32 [17, 1, 512, 8]

Streaming geometry: feature_frames per prediction = 17 (pre_encode_cache 9 + chunk 8), audio window 170 ms, constant cache length 70, d_model=512, 17 conformer layers, ×8 subsampling (80 ms/frame).

Compatibility (Xcode coremlc)

• model type: MLModelType_neuralNetwork
• storage precision: Float16
• specification version: 5
• availability: iOS 14.0, macOS 11.0

coremlc compile shenava_koochik_1_0_ctc_streaming_att70_0_ios15_fp16.mlmodel /tmp/out --deployment-target 15.0 --platform ios

Files

• shenava_koochik_1_0_ctc_streaming_att70_0_ios15_fp16.mlmodel — fp16 NeuralNetwork model (~212 MB)
• tokens.json, preprocessor.json, mel_filters_slaney_80x257.json — sidecars (ve_tok_v4, shared across the family)
• shenava_koochik_1_0_ctc_streaming_att70_0_ios15_fp16_manifest.json — export manifest
• export_koochik10_streaming_coreml.py — reproducible export script

Tokenizer: ve_tok_v4 (SentencePiece BPE-1024 +blank, digit/punct/«»-aware). Numbers are emitted in spoken form; apply Persian ITN at display for digits. Part of VisualEars / Shenava.

Export stack: coremltools 9.0, torch 2.7.0, NeMo 2.7.3. fp16 vs fp32 argmax agreement: 1.000.