On-device Russian automatic speech recognition. This repository packages the GigaAM v3 end-to-end RNN-T model compiled to Apple CoreML (.mlmodelc) for fast, fully offline inference on iOS and macOS (Apple Neural Engine / GPU / CPU).

The conversion changes only the serialization format (PyTorch → CoreML) and applies int8 weight quantization; the architecture and weights are unchanged.

Audio input is 16 kHz mono. The encoder is traced at a fixed 30 s shape, so shorter clips are zero-padded and longer audio must be chunked to ≤ 30 s before inference.

These are plain compiled CoreML models — load each with MLModel (or coremltools). The pipeline is: log-mel → Encoder → greedy RNN-T loop over Predictor + JointDecision, detokenized with vocab.txt.

This is a format conversion of salute-developers/GigaAM (GigaAM v3). All model credit belongs to the original authors. Please refer to the upstream repository for the authoritative model license and terms of use.