←Story detail

Trending story

IBM releases open-source speech model Granite Speech 5.0 2B

1 reports1 story updatesUpdated Oct 22 15:00

Understand this story

AI overview

IBM releases the open-source speech language model Granite Speech 5.0 2B, under the Apache 2.0 license, supporting speech-to-text in 6 languages and with speech translation capability. According to MarkTechPost, on the Open ASR Leaderboard the model ranks second among open-weight models with a 5.68% average English WER, behind only Qwen3-ASR-1.7B's 5.40%. Compared with 4.1 2B, it adds language ID prompting, keyword biasing of up to 2000 words, and on-demand punctuation and capitalization, and can run on Transformers, vLLM, llama.cpp and mlx-audio. There are currently no subsequent development facts.

AI-generated from public reports

Latest development · Report

IBM Releases Granite Speech 5.0 2B Multilingual Speech Transcription and Translation Model

Developments

1 confirmed developments

  1. IBM releases open-source speech model Granite Speech 5.0 2B

    Source:MarkTechPost

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Oct 22

  1. MarkTechPost

    IBM Releases Granite Speech 5.0 2B Multilingual Speech Transcription and Translation Model

    IBM has released the open-source speech language model Granite Speech 5.0 2B under the Apache 2.0 license. It supports speech-to-text in 6 languages and also offers speech translation capabilities. On the Open ASR Leaderboard, the model ranks second among open-weight models with an average English WER of 5.68%, behind only Qwen3-ASR-1.7B at 5.40%. Compared with 4.1 2B, it adds language ID prompting, keyword biasing of up to 2000 words, and on-demand punctuation and capitalization, and can run on Transformers, vLLM, llama.cpp, and mlx-audio.

Related stories

  1. Related storiesGradium open-sources on-device TTS model Phonon
  2. Related storiesBlock releases full-duplex speech model Dessa
  3. Related storiesBlock releases full-duplex speech model Dessa
  4. Related storiesNVIDIA Releases Open-Weight Speech Transcription Model Nemotron 3.5 Transcribe