Add model card

README.md

@@ -0,0 +1,89 @@
+---
+license: cc-by-4.0
+base_model: nvidia/canary-1b-v2
+pipeline_tag: automatic-speech-recognition
+library_name: coreml
+language:
+  - bg
+  - hr
+  - cs
+  - da
+  - nl
+  - en
+  - et
+  - fi
+  - fr
+  - de
+  - el
+  - hu
+  - it
+  - lv
+  - lt
+  - mt
+  - pl
+  - pt
+  - ro
+  - sk
+  - sl
+  - es
+  - sv
+  - ru
+  - uk
+tags:
+  - coreml
+  - apple-neural-engine
+  - on-device
+  - ios
+  - macos
+  - speech
+  - audio
+  - automatic-speech-recognition
+  - automatic-speech-translation
+  - canary
+  - fastconformer
+  - nemo
+  - kv-cache
+  - fp16
+---
+# Canary 1B v2 — CoreML (FP16, KV-cache)
+
+On-device CoreML port of NVIDIA **canary-1b-v2** for Apple silicon (iOS / macOS): FP32 preprocessor, FP16 Apple Neural Engine-resident FastConformer encoder, and a stateful KV-cache Transformer decoder driven by a host-side greedy loop. This is the reference (uncompressed) build; the memory-optimized variants below are derived from it and match its accuracy.
+
+**Base model:** [nvidia/canary-1b-v2](https://huggingface.co/nvidia/canary-1b-v2) (NVIDIA NeMo `EncDecMultiTaskModel`, 1B parameters, 25 European languages, ASR + speech translation). **License:** the base model is released under [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/legalcode.en); this conversion carries the same license. Please attribute NVIDIA for the model.
+
+## This build
+
+| | |
+|---|---|
+| Encoder | FP16 weights, Neural Engine-resident, 1.58 GB |
+| Decoder / cross-KV | FP16, 271 MB + 34 MB |
+| Download | 1.89 GB |
+| iOS RAM while transcribing | 1.9 GB (measured, 6-minute file) |
+
+## Build family
+
+All 1B v2 builds share the same preprocessor, tokenizer, package layout, and decode contract; only the weight format of the encoder and/or decoder differs. Download sizes are as hosted on the Hub; iOS RAM was measured in an app while transcribing a 6-minute file, or predicted from the Neural Engine-resident weight region where marked.
+
+| Repo | Build | Encoder weights | Decoder weights | Download | iOS RAM |
+|---|---|---|---|---|---|
+| **`canary-1b-v2-coreml` (this repo)** | FP16 (reference) | FP16 | FP16 | 1.89 GB | 1.9 GB (measured) |
+| [`canary-1b-v2-int8-coreml`](https://huggingface.co/smdesai/canary-1b-v2-int8-coreml) | INT8 encoder | INT8 per-channel | FP16 | 1.10 GB | 1.2 GB (measured) |
+| [`canary-1b-v2-pal6-coreml`](https://huggingface.co/smdesai/canary-1b-v2-pal6-coreml) | 6-bit encoder | 6-bit palette, g=16 | FP16 | 0.92 GB | 1.0 GB (measured) |
+| [`canary-1b-v2-int8full-coreml`](https://huggingface.co/smdesai/canary-1b-v2-int8full-coreml) | INT8 full | INT8 per-channel | INT8 per-channel | 0.95 GB | ~1.07 GB (predicted) |
+| [`canary-1b-v2-pal6-int8-coreml`](https://huggingface.co/smdesai/canary-1b-v2-pal6-int8-coreml) | 6-bit + INT8 | 6-bit palette, g=16 | INT8 per-channel | 0.77 GB | ~0.88 GB (predicted) |
+| [`canary-180m-flash-coreml`](https://huggingface.co/smdesai/canary-180m-flash-coreml) | 180M Flash | FP16 (17L, d=512) | FP16 (4L) | 0.37 GB | — |
+
+## Files
+
+| File | Contents |
+|---|---|
+| `canary_preprocessor.mlmodelc` | FP32 mel front end (128 mel bins, 16 kHz mono, 15 s window) |
+| `canary_encoder.mlmodelc` | FastConformer encoder, 32 layers, d=1024, subsampling 8 |
+| `canary_cross_kv.mlmodelc` | Cross-attention K/V projection, 8 layers (run once per window) |
+| `canary_decoder_kv.mlmodelc` | Stateful single-step Transformer decoder, 8 layers, 16384-way LM head |
+| `canary_spe.model` | SentencePiece tokenizer (16384 pieces) |
+| `metadata.json` | Shapes, decode geometry, seed tokens, and the weight recipe of this build |
+
+## Credits
+
+Model: NVIDIA NeMo team, [canary-1b-v2](https://huggingface.co/nvidia/canary-1b-v2), CC-BY-4.0.