Granite Speech 5.0: Transcribe, Translate, and Attribute more Accurately and Faster
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
★ Tier-1 Source
They're excited to share three updates to IBM's Granite Speech collection: a new speech-language model, granite-speech-5.0-2b, and revised versions of two models the community already uses, granite-speech-5.0-470m-turboctc and granite-speech-4.1-2b-plus.
Key facts
- Chart 1: granite-speech-5.0-2b ranks #2 among top open-weight ASR models on average English WER (5.06%)
- Chart 2: Average WER vs. RTFx on the Open ASR Leaderboard (English short-form, 9 public test sets, as of October 2026)
- They're excited to share three updates to IBM's Granite Speech collection: a new speech-language model, granite-speech-5.0-2b, and revised versions of two models the community already uses
- By compiling a single Conformer block and reusing its graph across the stack, they cut warmup time and pushed Turbo CTC to 19,870 RTFx on the Open ASR Leaderboard, up from roughly 12,600 RTFx
Summary
Granite-speech-5.0-2b is the successor to granite-speech-4.1-2b at the same parameter count. What's new compared with 4.1 2B Speech:. More accurate, more robust English ASR: Higher accuracy on English short-form benchmarks, and better handling of noise, reverberation, and distant-microphone speech. Language ID prompting: Name the input language in the prompt to steer multilingual transcription.