Omnilingual-ASR-CTC-1B-ONNX

soniqo/Omnilingual-ASR-CTC-1B-ONNX

Omnilingual-ASR-CTC-1B-ONNX is a automatic speech recognition model from soniqo. Use it when you need speech turned into text. It is set up for onnx. The card lists the license as cc-by-nc-4.0.

Meta omniASRCTC1Bv2 exported for server-side ONNX Runtime (CUDA EP with CPU fallback). Exported by models/omnilingual-asr/export/convertonnx.py in soniqo/speech-models.

Downloads · 30 days

12% of all-time downloads

All-time downloads

Public

Repo size

1 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.onnx1 GB · 100%

At a glance

Task: Automatic Speech Recognition
Library: onnx
License: cc-by-nc-4.0
Model type: omnilingual_asr_ctc
Access: Public
Created: Jul 13, 2026
Updated: Jul 13, 2026
SHA: 8f842c15

Model card

From the Hugging Face model README

Omnilingual ASR CTC 1B — ONNX (int8)

Meta omniASR_CTC_1B_v2 exported for server-side ONNX Runtime (CUDA EP with CPU fallback). Exported by models/omnilingual-asr/export/convert_onnx.py in soniqo/speech-models.

Graph


input	`audio` [1, S] f32 — 16 kHz waveform, z-scored by the caller
output	`logits` [1, T, 10288] — CTC logits, T = ceil(S / 320)

The time axis is dynamic: cost tracks the real clip length. (The LiteRT and CoreML exports bake a fixed window instead, because on-device wants a static shape.)

The caller must z-score the waveform — the graph does not normalise internally. Feeding raw audio scores 67.7% WER against 11.6% normalised.

Quality (FLEURS, 50 utts/language, Whisper normalizer)

	int8 ONNX (CPU, 8 threads)	fp32 PyTorch (GPU)
English	11.64	11.54
French	14.69	14.69
German	8.22	8.03
Arabic (ar_eg)	19.02	18.91

int8 costs ~0.1 WER: CTC is a single encoder pass, so there is no recurrent state for quantization error to accumulate through. Throughput is 17-21x realtime on 8 CPU threads.

Task: Automatic Speech Recognition
Library: onnx
Type: omnilingual_asr_ctc
License: cc-by-nc-4.0
Created: Jul 13, 2026
Updated: Jul 13, 2026