feat: add streaming STT service with Whisper backend

- stt_streaming.py: HTTP-based STT using external Whisper service
- stt_streaming_local.py: ROCm-based local Whisper inference
- Voice Activity Detection (VAD) with WebRTC
- Interrupt detection for barge-in support
- Session state management (listening/responding)
- OpenTelemetry instrumentation with HyperDX support
- Dockerfile variants for HTTP and ROCm deployments

requirements.txt

@@ -0,0 +1,20 @@
+nats-py>=2.0.0,<3.0.0
+httpx>=0.20.0,<1.0.0
+msgpack
+
+# Audio processing
+numpy>=1.20.0,<2.0.0
+webrtcvad>=2.0.10
+# pyannote.audio>=3.1.0  # Optional: for advanced speaker diarization
+
+# OpenTelemetry core
+opentelemetry-api
+opentelemetry-sdk
+
+# OTEL exporters (gRPC for local collector, HTTP for HyperDX)
+opentelemetry-exporter-otlp-proto-grpc
+opentelemetry-exporter-otlp-proto-http
+
+# OTEL instrumentation
+opentelemetry-instrumentation-httpx
+opentelemetry-instrumentation-logging