granite-speech-4.1-nar

About

What granite-speech-4.1-nar is

Granite-Speech-4.1-2B-NAR Model Summary: Granite-Speech-4.1-2B-NAR is a non-autoregressive (NAR) speech recognition model that formulates ASR as conditional transcript editing. Instead of decoding tokens one at a time, it edits a CTC hypothesis in a single forward pass using a bidirectional LLM, achieving competitive accuracy with faster inference than autoregressive alternatives. The model is based on the NLE (Non-autoregressive LLM-based Editing) architecture described in this paper. For applications where accuracy is the primary concern, consider granite-speech-4.1-2b, an autoregressive model from the Granite Speech 4.1 family which achieves higher transcription accuracy at the cost of increased inference latency. Granite-speech-4.1-2b produces punctuated and capitalized transcripts, supports AST and keyword-biased recognition, and includes Japanese. When speaker or word-timing information is needed, consider using granite-speech-4.1-2b-plus, which extends the above model with speaker-attributed ASR (speaker labels + word transcripts) and word-level timing information. Release Date: April 2026 License: Apache 2.0 Supported Languages: English, French, German, Spanish, Portuguese Intended Use: The model is intended for automatic speech recognition tasks, particularly in latency-sensitive applications where fast inference is critical. Evaluation Results Open ASR leaderboard results RTFx-WER results on the Open ASR leaderboard (as of Apr 2026). Additional results Greedy decoding with bfloat16 inference. WER computed with jiwer after whispernormalizer EnglishTextNormalizer normalization. Open ASR Leaderboard results may differ slightly due to normalization and scoring pipeline differences. Measured RTFx of ~1820 on a single H100 GPU (batched inference, batch size 128). Usage Installation We require flashattention2 for inference, since this backend supports sequence packing and respects the iscausal=False flag. Requires transformers=5.5.3 and torch=2.9.1. Inference with transformers Model Architecture The architecture consists of three components: (1) CTC Speech Encoder (440M params) A 16-layer Conformer encoder trained with CTC on character-level targets. It proce

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How embedding models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys granite-speech-4-1-nar for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (granite-speech-4-1-nar below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"granite-speech-4-1-nar","input":"text to embed"}'

Details

Languages, data & research

Papers

Licence

Open weights

Sources

Weights & code

Explore

More embedding models