#asr

Cohere has entered the speech stack race with Transcribe, a 2B Apache 2.0 ASR model for 14 languages. Open weights, Hugging Face distribution, and a claimed 5.42 average WER headline the release.

Cohere announced Transcribe on March 26, 2026 as an open-source speech recognition model. Cohere says the 2B Conformer-based system supports 14 languages, tops the Hugging Face Open ASR Leaderboard with 5.42 average WER, ships under Apache 2.0, and is available for download, API use, and Model Vault deployment.

IBM unveiled Granite 4.0 1B Speech on March 9, 2026 as a compact multilingual speech-language model for ASR and bidirectional speech translation. The company says it improves English transcription accuracy over its predecessor while cutting model size in half and adding Japanese support.

A Show HN post spotlighted Moonshine Voice, an open-source speech toolkit claiming strong accuracy and latency across edge and desktop devices. The project positions itself as a practical alternative to larger Whisper deployments for real-time voice apps.