Fix WebSocket streaming - ParlerTTSStreamer yields numpy arrays not tensors

Add comprehensive WebSocket testing suite and documentation

Add WebSocket endpoint for true real-time bidirectional streaming

Implement official ParlerTTSStreamer for true real-time audio streaming

Revert to sentence-by-sentence processing with fp16 - preserves word quality while maintaining speed

Optimize TTS for speed - add fp16, batch processing, remove sentence splitting

Add Urdu TTS test suite - generates audio files and saves to output folder

Add HF_TOKEN authentication for gated model access

Add fastapi to requirements

Simplify Dockerfile - use python:3.11 with straightforward setup

Use python:3.10 base with extended pip timeout for large packages

Switch to conda base image for faster PyTorch installation

Simplify Dockerfile and requirements - remove redundant dependencies for HF Spaces build

Add comprehensive test suite for TTS API audio validation

Use Python base image with pip-installed PyTorch for more reliable builds

Update Docker image to pytorch/pytorch:2.3.1-cuda12.1-runtime-ubuntu22.04

Optimize CUDA device handling - auto-detect GPU and remove unnecessary device transfers

Merge HF Space default README, keep API documentation

initial commit

Initial commit: Parler TTS FastAPI with Docker