--- license: apache-2.0 base_model: ibm-granite/granite-speech-4.1-2b pipeline_tag: automatic-speech-recognition library_name: openasr tags: - automatic-speech-recognition - speech-to-text - openasr - oasr - granite-speech ---
# Granite Speech 4.1 2B Β· OpenASR **IBM Granite Speech 4.1 β€” a 2B multilingual ASR model with strong English accuracy** [![License](https://img.shields.io/badge/license-Apache--2.0-2563eb.svg)](https://huggingface.co/ibm-granite/granite-speech-4.1-2b/blob/main/LICENSE) [![Format](https://img.shields.io/badge/format-.oasr-7c3aed.svg)](https://github.com/QuintinShaw/openasr) [![Runtime](https://img.shields.io/badge/runtime-OpenASR-111827.svg)](https://openasr.org) [![Base model](https://img.shields.io/badge/base-granite--speech--4.1--2b-f59e0b.svg)](https://huggingface.co/ibm-granite/granite-speech-4.1-2b) Native speech-to-text in the **[OpenASR](https://github.com/QuintinShaw/openasr)** runtime β€” engineered for peak performance on CPU & GPU, **no Python at inference time**.
--- ## ✨ Highlights - πŸ“Š **Verified English WER: 0.54%** β€” identical across fp16 / q8_0 / q4_k on OpenASR's frozen evaluation set - 🌐 **Six trained languages** β€” English, French, German, Spanish, Portuguese, Japanese (auto-detected; no language token) - πŸ“¦ **Three quantization tiers: fp16 / q8_0 / q4_k** β€” delivered in OpenASR's native .oasr format for local inference - πŸ¦€ **Native in OpenASR** β€” `.oasr` packs run with no Python at inference, engineered for peak performance on CPU & GPU ## πŸš€ Quickstart ```bash # 1. Install the OpenASR CLI Β· https://openasr.org # 2. Pull a build (pick a quant β€” see the table below) openasr pull granite-speech-4.1-2b:q8 # 3. Transcribe openasr transcribe audio.wav --model granite-speech-4.1-2b ``` All builds for this model: ```bash openasr pull granite-speech-4.1-2b:fp16 openasr pull granite-speech-4.1-2b:q8 openasr pull granite-speech-4.1-2b:q4 ``` ## πŸ“¦ Available builds | Quant | File (`.oasr`) | Size | RAM peak | RTF Β· M1 CPU | RTF Β· M1 GPU | JFK Ξ”WER vs fp16 | |:------|:---------------|-----:|---------:|-------------:|-------------:|-----------------:| | fp16 | `granite-speech-4.1-2b-fp16.oasr` | 4.63 GB | 5.91 GB | 0.40Γ— | 0.23Γ— | 0.0% | | q8_0 | `granite-speech-4.1-2b-q8_0.oasr` | 2.47 GB | 3.65 GB | 0.35Γ— | 0.17Γ— | 0.0% | | q4_k | `granite-speech-4.1-2b-q4_k.oasr` | 1.55 GB | 2.63 GB | 0.29Γ— | 0.15Γ— | 0.0% | RTF = real-time factor on the fixed 11s JFK clip (**lower is faster**); RAM peak measured per pack in an isolated subprocess. JFK Ξ”WER compares each quantized build's JFK transcript to this model's fp16 JFK transcript, so it measures quantization drift rather than absolute recognition accuracy. **q8_0** is the recommended default β€” near-reference quality at a fraction of the footprint. ## 🧠 About Granite Speech 4.1 2B Granite Speech 4.1 2B is a speech-recognition model from IBM Granite. Its architecture pairs a 16-layer Conformer audio encoder with a Q-Former projector feeding a 2B Granite decoder. The model auto-detects the source language through free-text instruction-following and ships trained coverage for English, French, German, Spanish, Portuguese, and Japanese. OpenASR distributes this model in three quantization tiers -- fp16, q8_0, and q4_k -- packaged in the native `.oasr` runtime format for local inference. ## βš™οΈ How these packs were made Converted from [ibm-granite/granite-speech-4.1-2b](https://huggingface.co/ibm-granite/granite-speech-4.1-2b) with the OpenASR importer: ```bash openasr model-pack core: convert_local_granite_speech_source_to_runtime_pack .oasr \ --package-id granite-speech-4.1-2b --quantization {fp16,q8-0,q4-k} ``` The `.oasr` container is GGUF-backed; packs use zero-copy mmap weight binding and graph buffer reuse to keep peak memory low. ## βš–οΈ License These packs **inherit the upstream model's license: Apache-2.0** ([source](https://huggingface.co/ibm-granite/granite-speech-4.1-2b/blob/main/LICENSE)). OpenASR packaging retains the upstream copyright and NOTICE; the only modifications are format conversion and quantization. ## πŸ™ Acknowledgements This pack is a redistribution of **granite-speech-4.1-2b**, created and released by **IBM Granite** ([ibm-granite/granite-speech-4.1-2b](https://huggingface.co/ibm-granite/granite-speech-4.1-2b)) under the [Apache License 2.0](https://huggingface.co/ibm-granite/granite-speech-4.1-2b/blob/main/LICENSE). OpenASR performs format conversion, quantization, runtime validation, and local-inference adaptation only; all model weights and training are the work of the original authors. ## πŸ”— Links - πŸ¦€ **OpenASR** β€” - 🌐 **Website** β€” - πŸ€— **Upstream model** β€” [ibm-granite/granite-speech-4.1-2b](https://huggingface.co/ibm-granite/granite-speech-4.1-2b)