FluidInference / canary-1b-v2-coreml

huggingface.co
Total runs: 0
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: June 17 2026
automatic-speech-recognition

Introduction of canary-1b-v2-coreml

Model Details of canary-1b-v2-coreml

Canary-1B-v2 — CoreML (ANE)

CoreML conversion of nvidia/canary-1b-v2 for Apple Silicon / Neural Engine, packaged for FluidAudio .

Canary is a FastConformer encoder + Transformer attention encoder-decoder (AED) ASR model (25 European languages, 16384-token SentencePiece BPE). It is decoded autoregressively: the transformer decoder cross-attends to the encoder output and emits tokens greedily until EOS (id 3), with a 1024→16384 projection head.

Files
File Role Precision
Preprocessor.mlmodelc waveform [1,240000] → mel [1,128,1501] fp32 (CPU)
EncoderInt4.mlmodelc mel → encoder [1,1024,188] int4 (ANE, iOS18)
DecoderInt4.mlmodelc autoregressive transformer → hidden [1,256,1024] int4 (ANE, iOS18)
Projection.mlmodelc hidden [1,1024] → logits [1,16384] fp16 (ANE)
vocab.json 16384 SentencePiece pieces ( id → piece ) —
projection_weights.npz raw projection weights (for Python reference pipelines) fp32
metadata.json shapes, sample rate, special token ids —

Contract: 15 s window (240000 samples @ 16 kHz), 256 decoder steps, eos=3 , pad=2 , bos=4 . int4 weight payloads require iOS 18 / macOS 15 .

Variants
  • int4 (this default): ANE-runnable, ~573 MB, fastest. Per-block-32 symmetric.
  • fp16 : exact parity with PyTorch, iOS 17, ~1.8 GB (not included here by default).
  • int8 per-channel decodes correctly only on CPU (crashes the GPU/ANE MPSGraph backend), so it is not recommended; use int4 for an ANE-resident small build.
Accuracy / speed (LibriSpeech test-clean, ≤15 s, int4, M-series ANE)
Metric Value
WER ~2.1%
RTFx ~7x

fp16 CoreML output is byte-identical to the NeMo PyTorch greedy decode.

Usage (FluidAudio)
let manager = try await CanaryManager.load(precision: .int4)
let text = try await manager.transcribe(audioURL: url)
Conversion

See the mobius conversion pipeline ( models/stt/canary-1b-v2/coreml/ ): convert-coreml.py (NeMo→CoreML), quantize_int4.py , build_projection.py , validate.py , stage_hf.py .

License

Inherits cc-by-4.0 from the base model nvidia/canary-1b-v2 .

Runs of FluidInference canary-1b-v2-coreml on huggingface.co

0
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About canary-1b-v2-coreml huggingface.co Model

More canary-1b-v2-coreml license Visit here:

https://choosealicense.com/licenses/cc-by-4.0

canary-1b-v2-coreml huggingface.co

canary-1b-v2-coreml huggingface.co is an AI model on huggingface.co that provides canary-1b-v2-coreml's model effect (), which can be used instantly with this FluidInference canary-1b-v2-coreml model. huggingface.co supports a free trial of the canary-1b-v2-coreml model, and also provides paid use of the canary-1b-v2-coreml. Support call canary-1b-v2-coreml model through api, including Node.js, Python, http.

FluidInference canary-1b-v2-coreml online free

canary-1b-v2-coreml huggingface.co is an online trial and call api platform, which integrates canary-1b-v2-coreml's modeling effects, including api services, and provides a free online trial of canary-1b-v2-coreml, you can try canary-1b-v2-coreml online for free by clicking the link below.

FluidInference canary-1b-v2-coreml online free url in huggingface.co:

https://huggingface.co/FluidInference/canary-1b-v2-coreml

canary-1b-v2-coreml install

canary-1b-v2-coreml is an open source model from GitHub that offers a free installation service, and any user can find canary-1b-v2-coreml on GitHub to install. At the same time, huggingface.co provides the effect of canary-1b-v2-coreml install, users can directly use canary-1b-v2-coreml installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

canary-1b-v2-coreml install url in huggingface.co:

https://huggingface.co/FluidInference/canary-1b-v2-coreml

Url of canary-1b-v2-coreml

Provider of canary-1b-v2-coreml huggingface.co

FluidInference
ORGANIZATIONS

Other API from FluidInference