scott
8de67c8bd9
Some checks failed
Build ROCm Image / build (push) Failing after 11s
ROCm 7.2 + PyTorch 2.11.0 has a bug where PyTorch passes workspace=0 to MIOpen convolutions, forcing fallback to the slow GemmFwdRest solver. This caused s3gen.inference to take 15-22s instead of <5s, making synthesis 3-4x slower than real-time audio playback. ROCm 6.1 allocates workspace correctly so MIOpen picks fast GEMM solvers without needing torch.compile workarounds. Changes: - Base image: rocm/dev-ubuntu-22.04:7.2 → 6.1 - torch 2.11.0 → 2.5.1 (rocm6.1 wheel index) - Add pytorch_triton_rocm==3.1.0 - transformers 5.2.0 → 4.46.3, safetensors 0.5.3 → 0.4.0 - s3tokenizer unpinned → 0.3.0 - resemble-perth==1.0.1 directly (v1.0.1 is pip-installable; drop stub) - Drop Dockerfile perth_stub steps - Drop torch.compile and timing patches from engine.py (not needed) - Drop multi-pass warmup from main.py (torch JIT warmup not needed) - Drop ROCm 7.2-specific env vars from docker-compose.yml Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
57 lines
1.6 KiB
Python
57 lines
1.6 KiB
Python
import asyncio
|
|
import logging
|
|
import sys
|
|
from functools import partial
|
|
|
|
from wyoming.server import AsyncServer
|
|
|
|
import engine
|
|
from config import get_wyoming_host, get_wyoming_port, load_config
|
|
from wyoming_handler import ChatterboxWyomingHandler
|
|
from wyoming_voices import create_wyoming_info, load_voices
|
|
|
|
logging.basicConfig(
|
|
level=logging.INFO,
|
|
format="%(asctime)s %(levelname)s %(name)s: %(message)s",
|
|
stream=sys.stdout,
|
|
)
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def _warmup(voices: dict) -> None:
|
|
"""Run one synthesis to populate MIOpen's in-memory kernel cache."""
|
|
from wyoming_voices import resolve_voice
|
|
audio_prompt = resolve_voice(None, voices) if voices else None
|
|
logger.info("Running warmup synthesis...")
|
|
try:
|
|
engine.synthesize(text="Warmup.", audio_prompt_path=audio_prompt)
|
|
logger.info("Warmup complete")
|
|
except Exception:
|
|
logger.warning("Warmup synthesis failed (non-fatal)", exc_info=True)
|
|
|
|
|
|
async def main() -> None:
|
|
load_config()
|
|
|
|
logger.info("Loading TTS model...")
|
|
if not engine.load_model():
|
|
logger.error("Failed to load model, exiting")
|
|
sys.exit(1)
|
|
|
|
voices = load_voices()
|
|
wyoming_info = create_wyoming_info(engine.get_sample_rate(), voices)
|
|
|
|
_warmup(voices)
|
|
|
|
host = get_wyoming_host()
|
|
port = get_wyoming_port()
|
|
uri = f"tcp://{host}:{port}"
|
|
|
|
logger.info(f"Starting Wyoming server on {uri}")
|
|
server = AsyncServer.from_uri(uri)
|
|
await server.run(partial(ChatterboxWyomingHandler, wyoming_info, voices))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main())
|