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

Add as a preferredsource on Google

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 Granite Speech 5.0 2B perform on benchmarks?

On the Open ASR Leaderboard, IBM’s chart shows a 5.68% average English WER. That average covers 9 public and 2 private test sets, as of October 21, 2026. Only Qwen3-ASR-1.7B scores better, at 5.40%.

Note a source conflict. IBM’s blog reports 5.06% instead. That figure is unofficial, dated October 15, and averages public short-form sets only.

Per-set results range widely. The model scores 0.99% on LibriSpeech Clean and 2.21% on LibriSpeech Other. It scores 13.79% on the private conversational set.

On the noisy FFASR leaderboard, it ranks #4 of 42 at 14.80% average WER. Qwen3-ASR-1.7B scores 13.41% there.

Multilingual CommonVoice WER is 2.60% for Portuguese and 3.50% for Spanish. Japanese is the weakest language at 10.74%.

For translation, X-to-English CoVoST BLEU reaches 53.6 for Portuguese and 40.1 for German. English-to-Mandarin was not evaluated.

Keyword biasing shows the clearest gain. On Earnings-22, keyword F1 rises from 67.2 to 90.1 with correct keyword lists. With 2,000-term lists mixing correct and wrong terms, it still reaches 82.8.

How does it compare with other open ASR models?

FeatureGranite Speech 5.0 2BQwen3-ASR-1.7BCohere Transcribe 03-2026Canary-Qwen-2.5B

Size2B2.35B (Hub count)2.07B (Hub count)2.5B

LicenseApache 2.0Apache 2.0Apache 2.0 (gated)CC-BY-4.0

ASR languages630 + 22 Chinese dialects14English only

Speech translationYesNot disclosedNot disclosedNo

Open ASR avg WER (Oct 21, 2026)*5.68%5.40%5.77%5.94%

FFASR avg WER (Oct 18, 2026)*14.80%13.41%15.03%Not disclosed

Keyword biasingUp to 2,000 termsNot disclosedNot disclosedNot disclosed

Long audio~2 min segmentsLong audio supportedNot disclosed40 s max in training

*Leaderboard averages as charted in IBM’s model card from the Open ASR and FFASR leaderboards.

What changed in Turbo CTC and 4.1 2B Plus?

Granite Speech 5.0 Turbo CTC keeps its 470M footprint. It now transcribes 7 languages with native punctuation and capitalization. IBM compiled one Conformer block and reused its graph across the stack. That lifted throughput to 19,870 RTFx, up from about 12,600 at launch.

The updated Granite Speech 4.1 2B Plus is a drop-in weight update. Average timestamp shift falls from 210.86 to 98.54. Long-form WER drops from 13.53 to 10.22. Biased-keyword WER falls from 11.79 to 6.48.

How can developers deploy it?

Granite Speech 5.0 2B runs in Transformers, vLLM, llama.cpp and mlx-audio. For GGUF, IBM recommends Q8_0. Lower-bit quantizations lose accuracy on audio longer than about 1 minute.

Key Takeaways

#2 open-weight model on the Open ASR Leaderboard at 5.68% WER.

2B parameters, Apache 2.0, runs on GPU, Mac and local CPU.

2,000-term keyword biasing across all supported languages.

Turbo CTC reaches 19,870 RTFx and now covers 7 languages.

Qwen3-ASR-1.7B still leads on accuracy and noisy audio.

Asif RazzaqWebsite | + postsBio ⮌

Asif RazzaqRecursive Releases Flint, an Open-Weight 40B MoE Local Coding Model for Agents with 2.5B Active Params

Asif RazzaqGoogle Cloud Ships llm-d 1.0 With Cache-Aware Routing for TPU and GPU Fleets

RELATED ARTICLESMORE FROM AUTHOR

A Coding Guide to Cactus Whistle: Does a 16.9 MB Speech Model Hold Up Against Whisper Base? Word Error Rate, Speed, Streaming, Timestamps, Keywords,...

Recursive Releases Flint, an Open-Weight 40B MoE Local Coding Model for Agents with 2.5B Active Params