Spaces:
Sleeping
Sleeping
File size: 3,383 Bytes
19933fe 2886be7 19933fe 2886be7 19933fe 2886be7 19933fe 2886be7 19933fe 1c7725b 19933fe | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 | """CLI entry point for the Reader server."""
from __future__ import annotations
import argparse
import sys
def main() -> int:
"""Main entry point for the Reader CLI.
Returns:
Exit code (0 for success).
"""
parser = argparse.ArgumentParser(
prog="reader",
description="PDF-to-Speech web server - listen to any content",
)
parser.add_argument(
"--voice",
type=str,
default=None,
help="Voice name for TTS. Options: Vivian, Serena, Uncle_Fu, Dylan, Eric, "
"Ryan, Aiden, Ono_Anna, Sohee (default: auto based on language)",
)
parser.add_argument(
"--language",
type=str,
default="english",
choices=["english", "chinese", "japanese", "korean"],
help="Language for TTS (default: english). Sets default voice if --voice not specified.",
)
parser.add_argument(
"--host",
type=str,
default="0.0.0.0",
help="Host to bind the server to (default: 0.0.0.0)",
)
parser.add_argument(
"--port",
type=int,
default=8000,
help="Port to bind the server to (default: 8000)",
)
parser.add_argument(
"--device",
type=str,
default="auto",
choices=["auto", "cuda", "cpu"],
help="Device to run the TTS model on (default: auto, detects GPU)",
)
parser.add_argument(
"--reload",
action="store_true",
help="Enable auto-reload for development",
)
args = parser.parse_args()
# Auto-detect device if set to 'auto'
device = args.device
if device == "auto":
try:
import torch
if torch.cuda.is_available():
device = "cuda"
print("🎮 GPU detected, using CUDA")
else:
device = "cpu"
print("💻 No GPU detected, using CPU (slower but works!)")
except ImportError:
device = "cpu"
print("💻 PyTorch not available for detection, using CPU")
print("🚀 Starting Reader server...")
print(f" Language: {args.language}")
print(f" Voice: {args.voice or 'auto'}")
print(f" Device: {device}")
print(f" URL: http://{args.host}:{args.port}")
print()
# Import here to avoid slow startup for --help
import uvicorn
from talking_snake.app import create_app
from talking_snake.tts import QwenTTSEngine
# Initialize TTS engine
print("📦 Loading TTS model (this may take a moment)...")
try:
tts_engine = QwenTTSEngine(
voice=args.voice,
language=args.language,
device=device,
)
except Exception as e:
print(f"❌ Failed to load TTS model: {e}", file=sys.stderr)
return 1
print("✅ TTS model loaded!")
# Run calibration to get accurate time estimates
print("⏱️ Calibrating speech timing...")
try:
tts_engine.calibrate()
except Exception as e:
print(f"⚠️ Calibration failed (using defaults): {e}")
print()
# Create app with engine
app = create_app(tts_engine=tts_engine)
# Run server
uvicorn.run(
app,
host=args.host,
port=args.port,
log_level="info",
)
return 0
if __name__ == "__main__":
sys.exit(main())
|