You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
feat(asr): Add Cohere Transcribe INT8 model support
Add HuggingFace integration for Cohere Transcribe CoreML models with INT8 quantization support.
Changes:
- Add CohereTranscribe model names enum with encoder, decoder, and vocab
- Add Cohere repository definitions (FP16 and INT8 variants)
- Update CohereAsrModels to use stateful decoder from HuggingFace
- Support automatic download from FluidInference/cohere-transcribe-03-2026-coreml
Model details:
- 35-second window architecture (3500 frames → 438 encoder outputs)
- INT8 W8A16 quantization (~2.0 GB vs ~4.2 GB FP16)
- 14-language support with token primer system
- Quality: 16.44% WER on LibriSpeech test-clean (INT8)
0 commit comments