IBM's open-source Granite Speech 5.0 2B enables accurate, multilingual transcription and translation, offering developers flexible, on-device speech processing capabilities.
AI-generated summary. Check the original reporting for context and accuracy.
This is the available feed excerpt, which may be shortened or in the publisher’s original language.
IBM has released Granite Speech 5.0 2B, a new open speech-language model for transcription and translation. Granite Speech 5.0 2B is a 2B-parameter model from IBM that turns speech into text in 6 languages. It ships under Apache 2.0. IBM also updated 2 existing models: the edge-focused Turbo CTC and the diarization-focused 4.1 2B Plus. For developers, the release covers accurate transcription, fast on-device transcription and speaker-attributed transcripts. TL;DR Size: 2B parameters, dense. LLM backbone uses YaRN extension to 16k positions. IBM recommends audio segments of up to about 2 minutes. Runs on: GPU via Transformers or vLLM, Apple Silicon via mlx-audio, local CPU/Mac via llama.cpp GGUF (Q8_0 recommended). Performance: #2 open-weight model on the Open ASR Leaderboard, 5.68% average English WER. Best: 0.99% WER on LibriSpeech Clean. Worst: 13.79% WER on the leaderboard’s private conversational set. How does Granite Speech 5.0 2B work? The model has 3 parts, per the model card. A speech encoder of 16 Conformer blocks is trained with CTC. It uses block attention over 4-second audio blocks. A 2-layer window q-former then projects and downsamples the acoustic embeddings. Total downsampling is 10x, so the LLM sees embeddings at 10 Hz. The LLM is an intermediate checkpoint of granite-4.0-1b-base. IBM extended it to 16k positions with YaRN and fine-tuned it with LoRA adapters. Training used 390,000 hours of public audio plus synthetic data. The synthetic sets target Japanese ASR, keyword biasing and translation. Training took 40 days on 8 H100 GPUs. What is new versus Granite Speech 4.1 2B? Language ID prompting: name the input language in the prompt to steer transcription. Keyword lists up to 2,000 terms: bias output toward product names, people and acronyms. Punctuation and capitalization on request: capitalization F1 runs from 90.16 to 99.51 across test sets. Robustness: better handling of noise, reverberation and distant microphones. How does Gr
An automated sorting aid based on source trust, keywords, and entities, on a scale of 1–12. High: 9–12; medium: 6–8; low: 1–5. It does not measure urgency, verify reporting, or indicate editorial endorsement.
IBM Granite time-series models use ensemble forecasting to combine multiple predictions, improving accuracy and reliability for complex time-series data analysis.
JOLT cuts training costs by 6.5x while matching accuracy, making large-scale language model reinforcement learning significantly more efficient and affordable.
This matters because it validates whether a tiny, CPU-friendly speech model can genuinely outperform larger competitors, enabling efficient, low-cost transcription for developers.