Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,9 @@ Step-Audio R1.1 (Realtime) is a major upgrade to Step-Audio-R1, designed for int
|
|
| 18 |
|
| 19 |
Unlike conventional streaming speech models that trade intelligence for latency, R1.1 enables *thinking while speaking*, achieving high intelligence without sacrificing speed.
|
| 20 |
|
|
|
|
|
|
|
|
|
|
| 21 |
### Mind-Paced Speaking (Low Latency)
|
| 22 |
Based on the research [*Mind-Paced Speaking*](MPS.pdf), the Realtime variant adopts a **Dual-Brain Architecture**:
|
| 23 |
- A **Formulation Brain** responsible for high-level reasoning
|
|
|
|
| 18 |
|
| 19 |
Unlike conventional streaming speech models that trade intelligence for latency, R1.1 enables *thinking while speaking*, achieving high intelligence without sacrificing speed.
|
| 20 |
|
| 21 |
+
|
| 22 |
+
WeChat Developer Group
|
| 23 |
+
|
| 24 |
### Mind-Paced Speaking (Low Latency)
|
| 25 |
Based on the research [*Mind-Paced Speaking*](MPS.pdf), the Realtime variant adopts a **Dual-Brain Architecture**:
|
| 26 |
- A **Formulation Brain** responsible for high-level reasoning
|