Audio modelOpen weights
Audio8-ASR-Infinite
Edge0 AI
- Released
- -
- Data date
- October 3, 2026
- Model class
- Access
Audio8-ASR-Infinite is an open streaming specialist for Chinese and English speech recognition. Its card targets ongoing, near-unbounded audio streams and returns transcript text rather than audio.
The model can run locally from the published Edge0-AI checkpoint. Apache-2.0 covers the weights and source code. This is a preview release, with the formal launch of semantic perception features still pending according to the project.
Specifications and access
| Specification | Value and source |
|---|---|
| Model class | Streaming speech recognitionSource |
| Access | Local weightsSource |
| Input | Chinese and English audioSource |
| Output | Streaming transcriptSource |
| Checkpoint | Edge0/Audio8-ASR-InfiniteSource |
| License | Apache-2.0Source |
| Streaming | Designed for ongoing and near-unbounded ASR streamsSource |
| Repository | Source code is published in the Edge0-AI repositorySource |
| Lifecycle | Preview release of open weights; the formal semantic-perception release remains in progressSource |
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
CER (Show measurement, test conditions, and source)
- Source value
- 1.75
- Score
- 1.75
- Metric
- character error rate
- Unit
- %
- Benchmark version
- source version not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Audio8-ASR-Infinite model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Card benchmark
- Context
- Source-specific observation; it does not establish a compatible cross-model cohort.
WER (Show measurement, test conditions, and source)
- Source value
- 3.042
- Score
- 3.042
- Metric
- word error rate
- Unit
- %
- Benchmark version
- source version not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Audio8-ASR-Infinite model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Card benchmark
- Context
- Source-specific observation; it does not establish a compatible cross-model cohort.
WER (Show measurement, test conditions, and source)
- Source value
- 6.808
- Score
- 6.808
- Metric
- word error rate
- Unit
- %
- Benchmark version
- source version not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Audio8-ASR-Infinite model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Card benchmark
- Context
- Source-specific observation; it does not establish a compatible cross-model cohort.
Sources and data date
Every statement links to its underlying documentation or leaderboard.
| Type | Evidence and data date |
|---|---|
| Research status | Research date October 4, 2026. 1 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Additional source | Audio8-ASR-Infinite model card (retrieved October 3, 2026; October 4, 2026) · Audio8-ASR-Infinite model card · Editorial description reviewed October 3, 2026 |
| Additional source | Audio8-ASR-Infinite repository (retrieved October 3, 2026) · Audio8-ASR-Infinite repository · Editorial description reviewed October 3, 2026 |