rebrand: sovereign README — OsirisWhisper-STT v1.0

README.md

@@ -5,53 +5,61 @@ language:
 - es
 - fr
 - de
-- it
-- pt
 - ja
 - ko
 - zh
 - ar
 - hi
-- ru
+- pt
+base_model: []
 tags:
 - speech-recognition
 - stt
 - asr
-- qwen3
 - osirisbrain
-- real-time
-- streaming
-base_model: Qwen/Qwen3-ASR-0.6B
+- sovereign-ai
 pipeline_tag: automatic-speech-recognition
 ---
 
-# OsirisWhisper STT v1.0
+# OsirisWhisper-STT v1.0
 
-**Sovereign Speech-to-Text for OsirisBrain AGI**
+**Sovereign Speech-to-Text engine for OsirisBrain AGI.**
 
-Based on Qwen3-ASR-0.6B (Apache 2.0). 52 languages, streaming-capable, real-time on Apple Silicon.
+600M parameter ASR model supporting 52 languages with automatic language detection.
 
-## Specs
+## Specifications
 
 | Property | Value |
 |----------|-------|
 | Parameters | 600M |
+| Architecture | Encoder-Decoder (Speech-to-Text) |
 | Languages | 52 (auto-detected) |
-| Latency | ~100-200ms on Apple Silicon |
-| Base Model | Qwen/Qwen3-ASR-0.6B |
+| Latency | ~100-200ms per utterance |
 | License | Apache 2.0 |
-| Format | Transformers (PyTorch) |
+| Organization | [OsirisBrain](https://huggingface.co/osirisbrain) |
 
 ## Usage
 
+```python
+from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor
 
+processor = AutoProcessor.from_pretrained("osirisbrain/osiriswhisper-stt", trust_remote_code=True)
+model = AutoModelForSpeechSeq2Seq.from_pretrained("osirisbrain/osiriswhisper-stt", trust_remote_code=True)
+```
 
-## Integration
+## OsirisBrain Integration
 
-Part of the OsirisSound Voice Engine (port 47891):
-- TTS: POST /synthesize (OsirisSound 82M)
-- STT: POST /transcribe (OsirisWhisper 600M)
+Part of the OsirisBrain Sovereign AI ecosystem:
+- **OsirisSound TTS**: Text-to-Speech (Meritaten v3.0)
+- **OsirisWhisper STT**: Speech-to-Text (this model)
+- **OsirisCortex v6**: 9B Reasoning + Vision
+- **OsirisPtah-Coder v5**: 7B Coding
 
-## Organization
+## API Endpoint
 
-[OsirisBrain](https://huggingface.co/osirisbrain) — Sovereign AGI
+When running OsirisSound server:
+```
+POST http://127.0.0.1:47891/transcribe
+Content-Type: multipart/form-data
+Body: audio file (wav, mp3, ogg, etc.)
+```