Image created with gemini-3.1-flash-image-preview with claude-sonnet-4-5. Image prompt: Using the provided reference image, preserve the exact weathered wooden crate with horizontal dark reddish-brown slats, iron hardware, and three-panel layout, but replace the original text with ‘COHERE’ in the same hand-painted black stencil style, and add small hand-painted words meaning ‘together’ in various scripts (Arabic, Chinese, Cyrillic, Bengali) on the crate’s edges and sides, place an open vintage multilingual dictionary beside the crate on muddy ground with early spring grass emerging, maintain the photorealistic 1950s documentary style with soft raking natural light and shallow depth of field.
Cohere Transcribe: state-of-the-art speech recognition https://cohere.com/blog/transcribe
Cohear 👂 Cohere’s first audio model. Apache 2.0. #1 on the Open ASR leaderboard. Multilingual transcription across 14 languages.
https://x.com/aidangomez/status/2037172942803701838
🎉 Congrats to @Cohere on releasing Cohere Transcribe, a 2B speech recognition model (Apache 2.0, 14 languages). Day-0 support in vLLM. Cohere contributed encoder-decoder serving optimizations to vLLM: variable-length encoder batching and packed attention for the decoder. Up to
https://x.com/vllm_project/status/2037197243111895066
Introducing: Cohere Transcribe – a new state-of-the-art in open source speech recognition.
https://x.com/cohere/status/2037159129345614174
New SoTa transcription model from @cohere! – #1 on accuracy on the Open ASR Leaderboard. – Open Source (Apache 2.0) – 14 Languages (English, French, Arabic, German, Italian, Spanish, Portuguese, Greek, Dutch, Polish, Chinese, Japanese, Korean, Vietnamese).
https://x.com/JayAlammar/status/2037172878165053951
Leave a Reply