Granite Speech 5.0 2B
A solid pick for self-hosting and full data control.
Overview
Granite Speech 5.0 2B was released on 21 October 2026 under the Apache 2.0 licence. It transcribes English, French, German, Spanish, Portuguese and Japanese, and translates speech between these languages. It was trained on 390,000 hours of public audio. On the Hugging Face Open ASR leaderboard it reaches a 5.06% average English word error rate, second among open models behind Qwen3-ASR 1.7B. You can supply up to 2,000 words of domain vocabulary to improve recognition of product names and acronyms. It runs with Transformers, vLLM, llama.cpp and mlx-audio on Mac. Known limit: accuracy drops on noisy audio and recordings longer than two minutes, so splitting beforehand is advised. For multi-speaker meetings, IBM recommends the 4.1 2B Plus variant, which identifies speakers.
Skill profile
Not disclosed
Strengths
- Open-source and self-hostable
Limitations
- No documented EU residency
- API pricing not disclosed
Who is it for
- you want to control cost or self-host
- you handle sensitive data with no EU option
Access & availability
Key specifications
What it costs per month
Estimate from sourced API prices and a hardware tier for self-hosting. Assumptions are editable.
Assumptions: 36-month amortisation, 0.25 €/kWh, 22 days/month, 1 $ = 0.92 €. Excludes labour, software licences, redundancy.
nAIvigate Trust Index
What the vendor offers and documents for professional use in Europe. An undocumented criterion counts as zero and stays visible: the score rises when the vendor publishes, not when we assume.
13/19 criteria documented · 68 % · 7 of them set by rule
See the criteria▾
Trust Index badge
Show this score in your docs, README or security page. It updates automatically.
[](https://naivigate.com/en/model/granite-speech-5-0-2b)Data & compliance
What we know, line by line, with source and date. These lines feed the Data and Enterprise families of the Trust Index above. GDPR compliance depends on your processing, not on the model alone.
| EU data residency | Not documented |
| Data processing agreement (DPA) | Not documented |
| Transfer outside the EU | Not documented |
| Training on your data | Not documented |
| Configurable retention | Not documented |
| Zero Data Retention | Not documented |
| Self-hostable | Yes |
| Declared hosting | self |
Quality of this card’s data
This score measures the quality of the data on this card: price, context, Elo, licence, documented, sourced and fresh. It measures neither the model nor its compliance: for that, see the Trust Index above.
1/8 documented · 1/8 primary sources
Run it locally
Deploy
Copy-ready commands generated from this card. Adjust context length and GPU count to your hardware.
OpenAI-compatible server for production on NVIDIA GPUs.
pip install vllm
vllm serve ibm-granite/granite-speech-5.0-2b \
--max-model-len 32768 \
--tensor-parallel-size 1 \
--dtype autoAdvanced data · for expertsArchitecture, modalities, detailed cost, full benchmarks▾
| Arena Elo | — |
| MMLU | — |
| GPQA | — |
| HumanEval | — |
| SWE-Bench | — |
| MATH | — |