server.py

from __future__ import annotations

import argparse
import gc
import json
import os
from pathlib import Path
import threading
from typing import Any

from fastapi import FastAPI, File, Form, HTTPException, UploadFile
from fastapi.responses import FileResponse
from fastapi.staticfiles import StaticFiles
import psutil

from asr_onnx_runtime import OnnxAsrEngine, OnnxCacheAsrEngine, collect_metrics


APP_DIR = Path(__file__).resolve().parent
STATIC_DIR = APP_DIR / "static"
ENGINE: OnnxAsrEngine | None = None
ENGINE_INFO: dict[str, Any] = {}
ENGINE_ARGS: argparse.Namespace | None = None
ENGINE_LOCK = threading.RLock()
PROCESS = psutil.Process()
SERVICE_PEAK_RSS = PROCESS.memory_info().rss
LAST_REQUEST_PEAK_RSS = SERVICE_PEAK_RSS


app = FastAPI(title="Audio8 ASR Local")
app.mount("/static", StaticFiles(directory=str(STATIC_DIR)), name="static")


def release_engine() -> None:
    global ENGINE
    ENGINE = None
    gc.collect()


class RequestMemorySampler:
    def __init__(self, sample_interval_s: float = 0.05) -> None:
        self.sample_interval_s = float(sample_interval_s)
        self.peak_rss_bytes = PROCESS.memory_info().rss
        self._stop = threading.Event()
        self._thread: threading.Thread | None = None

    def _run(self) -> None:
        while not self._stop.wait(self.sample_interval_s):
            self.peak_rss_bytes = max(self.peak_rss_bytes, PROCESS.memory_info().rss)

    def start(self) -> None:
        self.peak_rss_bytes = PROCESS.memory_info().rss
        self._thread = threading.Thread(target=self._run, daemon=True)
        self._thread.start()

    def stop(self) -> int:
        self.peak_rss_bytes = max(self.peak_rss_bytes, PROCESS.memory_info().rss)
        self._stop.set()
        if self._thread is not None:
            self._thread.join(timeout=1.0)
        return self.peak_rss_bytes


def update_service_peak(candidate: int | None = None) -> None:
    global SERVICE_PEAK_RSS
    current = PROCESS.memory_info().rss
    values = [SERVICE_PEAK_RSS, current]
    if candidate is not None:
        values.append(int(candidate))
    SERVICE_PEAK_RSS = max(values)


def available_cache_precisions(bundle_dir: str | Path) -> list[str]:
    bundle_path = Path(bundle_dir).expanduser().resolve()
    metadata_path = bundle_path / "metadata.json"
    if not metadata_path.exists():
        return []
    metadata = json.loads(metadata_path.read_text(encoding="utf-8"))
    prefill_graph = metadata.get("graphs", {}).get("lm_cache_prefill")
    graph = metadata.get("graphs", {}).get("lm_cache_decode")
    if not graph or not prefill_graph:
        return []
    prefill_graph_path = bundle_path / prefill_graph["path"]
    graph_path = bundle_path / graph["path"]
    values = []
    if prefill_graph_path.exists() and graph_path.exists():
        values.append("fp32")
    prefill_int8_path = prefill_graph_path.with_name(f"{prefill_graph_path.stem}_int8{prefill_graph_path.suffix}")
    int8_path = graph_path.with_name(f"{graph_path.stem}_int8{graph_path.suffix}")
    if prefill_int8_path.exists() and int8_path.exists():
        values.append("int8")
    prefill_int4_path = prefill_graph_path.with_name(f"{prefill_graph_path.stem}_int4{prefill_graph_path.suffix}")
    int4_path = graph_path.with_name(f"{graph_path.stem}_int4{graph_path.suffix}")
    if prefill_int4_path.exists() and int4_path.exists():
        values.append("int4")
    return values


def available_audio_precisions(bundle_dir: str | Path) -> list[str]:
    bundle_path = Path(bundle_dir).expanduser().resolve()
    metadata_path = bundle_path / "metadata.json"
    if not metadata_path.exists():
        return []
    metadata = json.loads(metadata_path.read_text(encoding="utf-8"))
    graphs = metadata.get("graphs", {})
    values = []
    fp32_graph = graphs.get("audio_hidden")
    if fp32_graph and (bundle_path / fp32_graph["path"]).exists():
        values.append("fp32")
    int8_graph = graphs.get("audio_hidden_int8")
    if int8_graph and (bundle_path / int8_graph["path"]).exists():
        values.append("int8")
    return values


def runtime_snapshot() -> dict[str, Any]:
    update_service_peak()
    bundle_dir = ENGINE_INFO.get("bundle_dir")
    return {
        **ENGINE_INFO,
        "runtime_loaded": ENGINE is not None,
        "available_cache_precisions": available_cache_precisions(bundle_dir) if bundle_dir else [],
        "available_audio_precisions": available_audio_precisions(bundle_dir) if bundle_dir else [],
        "service_peak_rss_bytes": int(SERVICE_PEAK_RSS),
        "last_request_peak_rss_bytes": int(LAST_REQUEST_PEAK_RSS),
    }


def load_engine(
    args: argparse.Namespace,
    *,
    backend: str | None = None,
    cache_precision: str | None = None,
    audio_precision: str | None = None,
    release_existing: bool = False,
) -> None:
    global ENGINE, ENGINE_INFO
    if release_existing:
        release_engine()
    selected_backend = backend or args.backend
    selected_precision = cache_precision or args.cache_precision
    selected_audio_precision = audio_precision if audio_precision is not None else getattr(args, "audio_precision", None)
    threads = args.threads if args.threads > 0 else None

    if selected_backend in {"auto", "onnx_cache"}:
        try:
            engine = OnnxCacheAsrEngine(
                args.bundle_dir,
                provider=args.provider,
                intra_op_num_threads=threads,
                cache_precision=selected_precision,
                audio_precision=selected_audio_precision,
            )
            ENGINE = engine
            ENGINE_INFO = {
                "bundle_dir": str(engine.bundle_dir),
                "backend": "onnx_cache",
                "cache_precision": engine.cache_precision,
                "cache_prefill_graph": str(engine.prefill_graph_path),
                "cache_graph": str(engine.cache_graph_path),
                "audio_precision": engine.audio_precision,
                "audio_graph": str(engine.audio_graph_path),
                "providers": engine.providers,
            }
            update_service_peak()
            return
        except Exception:
            if selected_backend == "onnx_cache":
                raise

    engine = OnnxAsrEngine(
        args.bundle_dir,
        provider=args.provider,
        intra_op_num_threads=threads,
        audio_precision=selected_audio_precision or "fp32",
    )
    ENGINE = engine
    ENGINE_INFO = {
        "bundle_dir": str(engine.bundle_dir),
        "backend": "onnx",
        "cache_precision": None,
        "cache_graph": None,
        "audio_precision": engine.audio_precision,
        "audio_graph": str(engine.audio_graph_path),
        "providers": engine.providers,
    }
    update_service_peak()


@app.get("/")
async def index() -> FileResponse:
    return FileResponse(STATIC_DIR / "index.html")


@app.get("/health")
async def health() -> dict[str, Any]:
    if ENGINE is None:
        return {"ok": False, "error": "engine not loaded"}
    return {"ok": True, **runtime_snapshot()}


@app.get("/api/runtime")
async def runtime() -> dict[str, Any]:
    return {"ok": ENGINE is not None, "runtime": runtime_snapshot()}


@app.post("/api/reload")
async def reload_runtime(
    backend: str = Form("onnx_cache"),
    cache_precision: str | None = Form(None),
    audio_precision: str | None = Form(None),
) -> dict[str, Any]:
    if ENGINE_ARGS is None:
        raise HTTPException(status_code=503, detail="Server arguments are not initialized")
    if backend not in {"onnx_cache", "onnx", "auto"}:
        raise HTTPException(status_code=400, detail=f"Unsupported backend: {backend}")
    if cache_precision:
        cache_precision = cache_precision.lower().strip()
        if cache_precision not in {"fp32", "int8", "int4", "auto"}:
            raise HTTPException(status_code=400, detail=f"Unsupported cache precision: {cache_precision}")
    else:
        cache_precision = str(ENGINE_INFO.get("cache_precision") or "").lower().strip() or ENGINE_ARGS.cache_precision
    if audio_precision:
        audio_precision = audio_precision.lower().strip()
        if audio_precision not in {"fp32", "int8", "auto"}:
            raise HTTPException(status_code=400, detail=f"Unsupported audio precision: {audio_precision}")
    else:
        audio_precision = str(ENGINE_INFO.get("audio_precision") or "").lower().strip() or None
    with ENGINE_LOCK:
        try:
            load_engine(
                ENGINE_ARGS,
                backend=backend,
                cache_precision=cache_precision,
                audio_precision=audio_precision,
                release_existing=True,
            )
        except Exception as exc:
            raise HTTPException(status_code=500, detail=str(exc)) from exc
    return {"ok": True, "runtime": runtime_snapshot()}


@app.get("/metrics")
async def metrics() -> dict[str, Any]:
    data = collect_metrics()
    data["runtime"] = runtime_snapshot()
    return data


@app.post("/asr")
async def asr(
    audio: UploadFile = File(...),
    language: str | None = Form(None),
    max_new_tokens: int = Form(128),
    cache_precision: str | None = Form(None),
    audio_precision: str | None = Form(None),
    hotwords: str | None = Form(None),
    hotword_topk: int = Form(50),
    hotword_start_boost: float = Form(6.0),
    hotword_continuation_boost: float = Form(8.0),
) -> dict[str, Any]:
    global LAST_REQUEST_PEAK_RSS
    if ENGINE is None:
        raise HTTPException(status_code=503, detail="ASR engine is not loaded")
    audio_bytes = await audio.read()
    if not audio_bytes:
        raise HTTPException(status_code=400, detail="Empty audio upload")
    if ENGINE_ARGS is not None:
        requested_cache = cache_precision.lower().strip() if cache_precision else None
        requested_audio = audio_precision.lower().strip() if audio_precision else None
        if requested_cache and requested_cache not in {"fp32", "int8", "int4", "auto"}:
            raise HTTPException(status_code=400, detail=f"Unsupported cache precision: {requested_cache}")
        if requested_audio and requested_audio not in {"fp32", "int8", "auto"}:
            raise HTTPException(status_code=400, detail=f"Unsupported audio precision: {requested_audio}")
        current_cache = str(ENGINE_INFO.get("cache_precision") or "").lower().strip()
        current_audio = str(ENGINE_INFO.get("audio_precision") or "").lower().strip()
        target_cache = requested_cache or current_cache or ENGINE_ARGS.cache_precision
        target_audio = requested_audio or current_audio or getattr(ENGINE_ARGS, "audio_precision", None)
        should_reload = (
            ENGINE_INFO.get("backend") == "onnx_cache"
            and (
                (requested_cache is not None and target_cache != current_cache)
                or (requested_audio is not None and target_audio != current_audio)
            )
        )
        if should_reload:
            with ENGINE_LOCK:
                try:
                    load_engine(
                        ENGINE_ARGS,
                        backend="onnx_cache",
                        cache_precision=target_cache,
                        audio_precision=target_audio,
                        release_existing=True,
                    )
                except Exception as exc:
                    raise HTTPException(status_code=500, detail=str(exc)) from exc
    sampler = RequestMemorySampler()
    sampler.start()
    try:
        with ENGINE_LOCK:
            if ENGINE is None:
                raise HTTPException(status_code=503, detail="ASR engine is not loaded")
            result = ENGINE.transcribe(
                audio_bytes,
                language=language or None,
                max_new_tokens=max_new_tokens,
                hotwords=hotwords or None,
                hotword_topk=int(hotword_topk),
                hotword_start_boost=float(hotword_start_boost),
                hotword_continuation_boost=float(hotword_continuation_boost),
            )
        LAST_REQUEST_PEAK_RSS = max(int(sampler.stop()), PROCESS.memory_info().rss)
        update_service_peak(LAST_REQUEST_PEAK_RSS)
        result["request_peak_rss_bytes"] = int(LAST_REQUEST_PEAK_RSS)
        result["runtime"] = runtime_snapshot()
        return result
    except Exception as exc:
        LAST_REQUEST_PEAK_RSS = max(int(sampler.stop()), PROCESS.memory_info().rss)
        update_service_peak(LAST_REQUEST_PEAK_RSS)
        raise HTTPException(status_code=500, detail=str(exc)) from exc


def parse_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser(description="Run the local Audio8 ASR ONNX web UI.")
    parser.add_argument(
        "--bundle_dir",
        default=os.environ.get("AUDIO8_ASR_BUNDLE", "model_bundle"),
    )
    parser.add_argument(
        "--backend",
        choices=["auto", "onnx", "onnx_cache"],
        default=os.environ.get("ASR_BACKEND", "auto"),
    )
    parser.add_argument("--host", default=os.environ.get("HOST", "127.0.0.1"))
    parser.add_argument("--port", type=int, default=int(os.environ.get("PORT", "7860")))
    parser.add_argument("--provider", default=os.environ.get("ORT_PROVIDER", "CPUExecutionProvider"))
    parser.add_argument("--cache_precision", default=os.environ.get("ASR_CACHE_PRECISION", "auto"))
    parser.add_argument("--audio_precision", choices=["fp32", "int8", "auto"], default=os.environ.get("ASR_AUDIO_PRECISION", "auto"))
    parser.add_argument("--threads", type=int, default=int(os.environ.get("ORT_THREADS", "0")))
    return parser.parse_args()


def main() -> None:
    global ENGINE_ARGS
    args = parse_args()
    ENGINE_ARGS = args
    load_engine(args)
    _run_uvicorn(args)


def _run_uvicorn(args: argparse.Namespace) -> None:
    import uvicorn

    uvicorn.run(app, host=args.host, port=args.port)


if __name__ == "__main__":
    main()