wowsuch ai
Live

Edge0 AIModel

Audio8 ASR Infinite

Audio8 ASR Infinite is a native streaming speech recognition model for Chinese and English. Its preview checkpoint supports selectable audio clocks, configurable transcription delay, and rolling KV caching for unlimited-length transcription.

What it does

Use it to transcribe Chinese or English audio in streaming or continuous 24/7 workflows.

Availability
Preview release; checkpoint available on Hugging Face
Pricing model
Not established
Deployment
Docker Compose deployment; local web demo and realtime client
Privacy
Not established
Licence
Apache 2.0
Capability
extraction
Modality
audiotext
Access
open weightswebCLI
Deployment
on-premises
Pricing
unknown
Target user
developerresearcher

Evidence

6 claims
  • The model supports Chinese and English transcription. [1]
  • Selectable audio clocks are 80, 120, or 160 ms, with configurable transcription delay. [1]
    | **Preview — ASR base** | ✅ done | Streaming Chinese/English transcription: selectable 80/120/160 ms clock, configurable `target_delay_ms`, unlimited-length rolling KV window |
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • Rolling KV Cache enables unlimited-length transcription with constant memory and latency, according to the source. [1]
    - **Unlimited-length transcription** — a rolling KV Cache keeps both **memory and
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The checkpoint is available on Hugging Face as a preview release.
  • The documented Docker Compose stack serves a local web demo and realtime service. [1]
    Docker compose is the canonical deployment path; it also serves the web demo:
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The source identifies Apache 2.0 as the license. [1]

Sources

1
1
Hugging FaceOwner-controlled
https://huggingface.co/Edge0/Audio8-ASR-Infinite Retrieved 2026-10-27 01:51 UTC
Verified

Versions

3
VersionEffectiveChangeChanged fieldsState
32026-10-22 00:40 UTCevidence updatescoreCurrent
22026-09-25 18:45 UTCmaterial changedeploymentCurrent
12026-09-24 19:44 UTCpublicationNoneCurrent

In briefs

1

Open in the catalog

Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.