IBM AI Released Open Source Voice Model
The story so far
IBM has released the open-source speech model Granite Speech 5.0 2B, which supports speech-to-text and translation in 6 languages. It ranks second on the Open ASR leaderboard, with an average WER of 5.68% for English. The model uses YaRN to extend to 16k positions, supports deployment on GPUs, Apple Silicon, and local CPUs, and includes 2000 keyword bias features. The model was trained on 390,000 hours of data and supports multilingual translation and deployment options.
AI-written from the reports · Updated 27 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- MarkTechPostIBM AI Releases Granite Speech 5.0 2B for Multilingual Transcription and Translation
IBM releases Granite Speech 5.0 2B, an open-source speech language model with 2B parameters, supporting speech-to-text and translation in 6 languages, ranking second on the Open ASR list, with an average WER of 5.68% for English. The model uses YaRN to extend to 16k positions, supports GPU, Apple Silicon, and local CPU deployment, and includes 2000 keyword bias features.
- Hugging Face BlogGranite Speech 5.0: Transcribe, Translate, and Attribute more Accurately and Faster
IBM released three models in the Granite Speech 5.0 series, with granite-speech-5.0-2b trained on 390,000 hours of data and supporting translation between 6 languages and 2.