Live transcription · Multilingual

Granite Speech 4.1 2B

IBM Granite Speech 4.1 — a 2B multilingual ASR model with strong English accuracy

Multilingual · 2.8× · 2.3 GB

Install in OpenASR Desktop

Opens the desktop app and downloads this model for you.

Don't have the app yet? Download OpenASR Desktop

On-deviceOn this computer
interview.m4a12:04

let's line up this week's release plan,

the beta build can ship on Friday,

then loop in design and QA,

Why it fits

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.

What you can do with it

  • 📊 Verified English WER: 0.54% — identical across fp16 / q8_0 / q4_k on OpenASR's frozen evaluation set
  • 🌐 Six trained languages — English, French, German, Spanish, Portuguese, Japanese (auto-detected; no language token)
  • 📦 Three quantization tiers: fp16 / q8_0 / q4_k — delivered in OpenASR's native .oasr format for local inference
  • 🦀 Native in OpenASR — .oasr packs run with no Python at inference, engineered for peak performance on CPU & GPU

Other models

Developer details CLI commands, file hashes, and per-quant downloads — for scripting and verification.

Downloads by quantization

Pull stringSizeQuant
granite-speech-4.1-2b:fp16 4.3 GB fp16
open .oasr
granite-speech-4.1-2b:q8default 2.3 GB q8_0
open .oasr
granite-speech-4.1-2b:q4 1.4 GB q4_k
open .oasr

Model facts

Size2.3 GB
Speed2.8× real-time
LanguageMultilingual
Familygranite-speech
Vendoribm-granite
Released2025-05-01
Peak memory3.4 GB
Quantizationq8_0
LicenseApache-2.0
Revision8f6743e1bec5819962d92588a18021f7c66b592c
sha2567368242e65f8f907bae8002a609f966a25fcb32af6575b1baae6057c48e6566c

Usage

These are CLI / local-server examples. The desktop app runs this model without typing a command — use Install above.

bash · transcribe a file
$ openasr pull granite-speech-4.1-2b:q8
↓ granite-speech-4.1-2b.oasr  2.3 GB  ✓ verified sha256
$ openasr transcribe meeting.wav --backend native --model-pack ~/.openasr/models/granite-speech-4.1-2b/q8_0/granite-speech-4.1-2b-q8_0.oasr
✓ local transcript · 0 bytes sent
bash · serve a local API
$ openasr serve --backend native --model-pack ~/.openasr/models/granite-speech-4.1-2b/q8_0/granite-speech-4.1-2b-q8_0.oasr --addr 127.0.0.1:8080
▶ http://127.0.0.1:8080 · model=granite-speech-4.1-2b · 0 bytes will leave this host
python · client.py
from openai import OpenAI
client = OpenAI(base_url="http://127.0.0.1:8080/v1", api_key="local")
audio = open("meeting.wav", "rb")
text = client.audio.transcriptions.create(model="granite-speech-4.1-2b", file=audio)