termux-stt 1.3.2 → 1.4.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +40 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -66,6 +66,46 @@ main();
|
|
|
66
66
|
|
|
67
67
|
---
|
|
68
68
|
|
|
69
|
+
## Distributed Clustering & Memory Pooling (AMEVA-Cluster)
|
|
70
|
+
|
|
71
|
+
Termux-STT natively integrates with **AMEVA-Cluster** (`pip install ameva-cluster`) for distributed large-model speech recognition (e.g. `whisper-large-v3-turbo`) across interconnected mobile fleets.
|
|
72
|
+
|
|
73
|
+
### 1. Install Cluster Runtime
|
|
74
|
+
```bash
|
|
75
|
+
pip install ameva-cluster
|
|
76
|
+
# or Node.js:
|
|
77
|
+
npm install @ameva/cluster
|
|
78
|
+
```
|
|
79
|
+
|
|
80
|
+
### 2. Launch Worker Node on Remote Phone
|
|
81
|
+
```bash
|
|
82
|
+
# On remote worker device (e.g. Galaxy A53):
|
|
83
|
+
ameva-cluster worker --port 50052
|
|
84
|
+
```
|
|
85
|
+
|
|
86
|
+
### 3. Distributed Transcription via Master Node
|
|
87
|
+
```bash
|
|
88
|
+
# Master node sharding Whisper-Large layers across remote phone RAM:
|
|
89
|
+
termux-stt transcribe meeting.wav \
|
|
90
|
+
--model whisper-large-v3-turbo.bin \
|
|
91
|
+
--rpc 192.0.2.10:50052,192.0.2.11:50052
|
|
92
|
+
```
|
|
93
|
+
|
|
94
|
+
```python
|
|
95
|
+
from termux_stt import create_engine
|
|
96
|
+
|
|
97
|
+
# Python SDK Distributed STT
|
|
98
|
+
engine = create_engine(
|
|
99
|
+
"whisper",
|
|
100
|
+
model="large-v3-turbo",
|
|
101
|
+
cluster_rpc_servers="192.0.2.10:50052,192.0.2.11:50052"
|
|
102
|
+
)
|
|
103
|
+
result = engine.transcribe("meeting.wav")
|
|
104
|
+
print(result.text)
|
|
105
|
+
```
|
|
106
|
+
|
|
107
|
+
---
|
|
108
|
+
|
|
69
109
|
## Official Documentation & Benchmarks
|
|
70
110
|
- [Official Architecture & API Reference](https://uno-km.vercel.app/lib/stt/)
|
|
71
111
|
- [Ecosystem Metrics & Registry Stats](https://uno-km.vercel.app/foundation/metrics)
|
package/package.json
CHANGED