Granite Speech 5.0: Transcribe, Translate, and Attribute more Accurately and Faster

Back to Articles

a]:hidden">

Granite Speech 5.0: Transcribe, Translate, and Attribute more Accurately and Faster

Enterprise Article Published October 21, 2026

Upvote 1

George Saon gsaon Follow

ibm-granite

Brian Kingsbury bedkingsbury Follow

ibm-granite

Ron Hoory rhoory Follow

ibm-granite

Vishal Sunder vishalsunder Follow

ibm-granite

Zvi Kons konszvi Follow

ibm-granite

Jeff Kuo ibm-jeffkuo Follow

ibm-granite

Samuel Thomas sthomas12 Follow

ibm-granite

Avihu Dekel Avihu Follow

ibm-granite

Hagai Aronowitz hagaia Follow

ibm-granite

Takashi Fukuda fukuda1 Follow

ibm-granite

Tohru Nagano tohru3 Follow

ibm-granite

Sashi Novitasari sasnov Follow

ibm-granite

Masayuki Suzuki szuk Follow

ibm-granite

Madison Lee kristunlee Follow

ibm-granite

:last-child]:mb-0"> Granite Speech 5.0 2B: more accurate, more robust, more control

Granite Speech 5.0 Turbo CTC: now multilingual, more robust, and even faster

Granite Speech 4.1 2B Plus: better at who said what, and when

Get started

We'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. Together they cover the full range of enterprise speech work: transcription and translation with high accuracy, extremely fast transcription at the edge, and recordings where who spoke, and when, matter as much as what was said.

Granite Speech 5.0 2B: more accurate, more robust, more control

granite-speech-5.0-2b is the successor to granite-speech-4.1-2b at the same parameter count. It transcribes English, French, German, Spanish, Portuguese, and Japanese, and translates to and from English in those languages, plus English to Italian and Mandarin. It was trained on 390,000 hours of public audio, plus synthetic data built for Japanese ASR, keyword biasing, and translation.

The model ships under Apache 2.0 with support in Transformers, vLLM, llama.cpp, and mlx-audio for Apple Silicon.

Chart 1: granite-speech-5.0-2b ranks #2 among top open-weight ASR models on average English WER (5.06%). Lower is better. Results are unofficial, as of 15 October 2026, and averaged over the Open ASR Leaderboard’s public English short-form test sets.

Granite Speech 5.0 Turbo CTC: now multilingual, more robust, and even faster

When we introduced Turbo CTC in August, it was an English-only, 470M-parameter encoder built for speed. This revision keeps that footprint and adds the three things users asked for most:

It's also faster. By compiling a single Conformer block and reusing its graph across the stack, we cut warmup time and pushed Turbo CTC to 19,870 RTFx on the Open ASR Leaderboard, up from roughly 12,600 RTFx at launch: about 1.6x faster, at the same accuracy level.

Chart 2: Average WER vs. RTFx on the Open ASR Leaderboard (English short-form, 9 public test sets, as of October 2026). Lower WER and higher RTFx are better; RTFx is on a log scale.

Granite Speech 4.1 2B Plus: better at who said what, and when

The updated granite-speech-4.1-2b-plus is tuned for the recordings enterprises actually have: meetings, support calls, and interviews with several speakers running long. It keeps the 4.1 name because the architecture, prompt format, and API are unchanged, so it's a drop-in replacement for the current model with improved weights. This revision improves four areas:

Table 1: All metrics are error rates, so lower is better. For more detailed results, see the model card.

Get started

Not sure which model to pick? Start here:

These models are all released under an Apache 2.0 license with native support in Transformers. Full evaluation results, architecture details, training data, and usage examples are on each model card. We recommend pairing them with Granite Guardian for production deployments that need additional risk detection.

Give them a try and let us know what you think!

Models mentioned in this article 3

ibm-granite/granite-speech-4.1-2b-plus

Automatic Speech Recognition • 2B • Updated 2 minutes ago • 34.5k • 94

ibm-granite/granite-speech-5.0-2b

Automatic Speech Recognition • 2B • Updated 31 minutes ago • 105

ibm-granite/granite-speech-5.0-470m-turboctc

Automatic Speech Recognition • 0.5B • Updated 35 minutes ago • 59.4k • 84

Collections mentioned in this article 1

Granite Guardian

Collection

Safety models for detecting risks, toxicity, and hallucinations in LLM workflows. • 15 items • Updated 6 days ago • 30

More from this author