---
title: "Edge0 Releases Audio8-ASR-0.1B to Run Speech Recognition on Any Phone"
subtitle: "A tiny 0.1B-parameter multilingual speech recognition model runs entirely on-device with a 200MB memory footprint on iPhones."
url: "https://alphasignal.ai/news/edge0-releases-audio8-asr-0-1b-to-run-speech-recognition-on-any-phone"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-07-10T06:57:05.000Z"
updated: "2026-09-13T02:06:07.055Z"
type: "Model"
topics:
  - "Audio"
  - "Gpus"
subtopics:
  - "Speech To Text"
  - "Edge Deployment"
upvotes: 315
source_url: "https://huggingface.co/Edge0/Audio8-ASR-0.1B"
comments: 0
truncated: true
---

# Edge0 Releases Audio8-ASR-0.1B to Run Speech Recognition on Any Phone

> A tiny 0.1B-parameter multilingual speech recognition model runs entirely on-device with a 200MB memory footprint on iPhones.

# Audio8-ASR-0.1B targets multilingual transcription on edge devices

Edge0 has released [Audio8-ASR-0.1B](https://huggingface.co/Edge0/Audio8-ASR-0.1B), a compact autoregressive speech-recognition model for phones, laptops, and other memory-constrained hardware. The release pairs a base Transformers checkpoint with ONNX Runtime, INT8, and iOS Neural Engine deployment options.

The model recognizes Chinese, English, French, German, Japanese, Korean, and Cantonese. Its decoder produces a transcript one token at a time from encoded audio and previously generated tokens. Local execution can reduce network latency and keep raw audio off remote servers when the surrounding application also avoids uploads and telemetry.

## A 103.5M decoder inside a 324M system

The 0.1B label identifies the language-model component, which contains about 103.5 million parameters. The complete speech-recognition pipeline contains about 324 million unique parameters after the audio encoder, adapter, and projector are included.

| Component             | Implementation                                                      |
| --------------------- | ------------------------------------------------------------------- |
| Audio encoder         | Backbone derived from Qwen3-ASR-0.6B                                |
| Adapter and projector | MLP components trained for Audio8-ASR                               |
| Language decoder      | Eight-layer Qwen-style causal model based on Ref-Pretrain-Qwen-104M |
| Decoder size          | Approximately 103.5 million parameters                              |
| Full pipeline size    | Approximately 324 million unique parameters                         |
| Audio rate            | 16 kHz                                                              |

The architecture reuses a larger model’s audio representation while keeping the text decoder small. That split explains how the release can carry a 0.1B name while requiring more memory than a standalone 100-million-parameter language model.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [Edge0/Audio8-ASR-0.1B on Hugging Face](https://huggingface.co/Edge0/Audio8-ASR-0.1B)
- [Audio8 organization page](https://huggingface.co/Audio8)
- [Samuel Zeng on X](https://x.com/SamuelZengML)
- [Audio8/Audio8-ASR-0.1B (mirror repo)](https://huggingface.co/Audio8/Audio8-ASR-0.1B)
- [Data-Efficient On-Policy Distillation for ASR](https://arxiv.org/abs/2605.28139)