Files
Aletheia/server/audiobook/audiobook_service.py
T

689 lines
25 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
from __future__ import annotations
import gc
import hashlib
import hmac
import html
import json
import os
import re
import secrets
import shutil
import sqlite3
import subprocess
import threading
import time
import uuid
import zipfile
from concurrent.futures import ThreadPoolExecutor
from contextlib import contextmanager
from pathlib import Path, PurePosixPath
from typing import TYPE_CHECKING, Annotated, Any, Iterator
from xml.etree import ElementTree
import imageio_ffmpeg
import soundfile as sf
from fastapi import Depends, FastAPI, File, Form, Header, HTTPException, UploadFile
from fastapi.responses import FileResponse
from num2words import num2words
if TYPE_CHECKING:
from qwen_tts import Qwen3TTSModel
ROOT = Path(os.environ.get("AUDIOBOOK_SERVICE_ROOT", "/home/sevenhill/apps/aletheia-audiobook"))
SERVICE_ROOT = ROOT / "service"
DATA_ROOT = ROOT / "audiobook-jobs"
TOKEN_FILE = SERVICE_ROOT / "service-token.txt"
DATABASE = DATA_ROOT / "jobs.db3"
PERFORMANCE_LOG = DATA_ROOT / "performance.jsonl"
MODEL_ID = os.environ.get("QWEN_TTS_MODEL_ID", "Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice")
MAX_UPLOAD_BYTES = 200 * 1024 * 1024
GPU_IDS = tuple(
int(value.strip())
for value in os.environ.get("QWEN_TTS_GPU_IDS", "0,1,2").split(",")
if value.strip()
)
SPEAKER = os.environ.get("QWEN_TTS_SPEAKER", "Ryan")
VOICE_INSTRUCTION = (
"Read in a calm, clear, natural audiobook style with steady pacing and distinct diction."
)
SERVICE_ROOT.mkdir(parents=True, exist_ok=True)
DATA_ROOT.mkdir(parents=True, exist_ok=True)
OLLAMA_PAUSE_MARKER = SERVICE_ROOT / "ollama-paused-for-audiobook"
if not TOKEN_FILE.exists():
TOKEN_FILE.write_text(secrets.token_urlsafe(48), encoding="ascii")
API_TOKEN = TOKEN_FILE.read_text(encoding="ascii").strip()
def pause_ollama_for_audiobook() -> None:
"""Release every CMP GPU before loading the three Qwen workers."""
subprocess.run(["systemctl", "--user", "stop", "ollama.service"], check=True)
subprocess.run(["systemctl", "--user", "mask", "--runtime", "ollama.service"], check=True)
OLLAMA_PAUSE_MARKER.write_text("1", encoding="ascii")
def restore_ollama_after_audiobook() -> None:
if not OLLAMA_PAUSE_MARKER.exists():
return
subprocess.run(["systemctl", "--user", "unmask", "--runtime", "ollama.service"], check=True)
subprocess.run(["systemctl", "--user", "start", "ollama.service"], check=True)
OLLAMA_PAUSE_MARKER.unlink(missing_ok=True)
# The worker terminates after every job to release CUDA/Triton contexts. The
# next lightweight receiver process restores Ollama before accepting new work.
restore_ollama_after_audiobook()
app = FastAPI(title="Aletheia CMP Audiobook Service", version="1.1.0")
queue_condition = threading.Condition()
queued_jobs: list[str] = []
worker_state = {"activeJobId": None, "modelLoaded": False}
@contextmanager
def database() -> Iterator[sqlite3.Connection]:
connection = sqlite3.connect(DATABASE, timeout=30)
connection.row_factory = sqlite3.Row
try:
yield connection
connection.commit()
finally:
connection.close()
def initialize_database() -> None:
with database() as connection:
connection.execute(
"""
CREATE TABLE IF NOT EXISTS jobs (
id TEXT PRIMARY KEY,
title TEXT NOT NULL,
author TEXT NOT NULL,
source_name TEXT NOT NULL,
input_path TEXT NOT NULL,
output_path TEXT NOT NULL,
status TEXT NOT NULL,
stage TEXT NOT NULL,
processed_characters INTEGER NOT NULL DEFAULT 0,
total_characters INTEGER NOT NULL DEFAULT 0,
current_chapter TEXT,
duration_ms INTEGER NOT NULL DEFAULT 0,
chapters_json TEXT NOT NULL DEFAULT '[]',
error_message TEXT,
cancel_requested INTEGER NOT NULL DEFAULT 0,
created_at INTEGER NOT NULL,
updated_at INTEGER NOT NULL
)
"""
)
connection.execute(
"UPDATE jobs SET status='queued', stage='queued' "
"WHERE status IN ('extracting','synthesizing','encoding')"
)
rows = connection.execute(
"SELECT id FROM jobs WHERE status='queued' ORDER BY created_at"
).fetchall()
queued_jobs.extend(row["id"] for row in rows)
def require_token(authorization: Annotated[str | None, Header()] = None) -> None:
expected = f"Bearer {API_TOKEN}"
if not authorization or not hmac.compare_digest(authorization, expected):
raise HTTPException(status_code=401, detail="Invalid API token")
def now_ms() -> int:
return int(time.time() * 1000)
def get_job(job_id: str) -> sqlite3.Row:
with database() as connection:
row = connection.execute("SELECT * FROM jobs WHERE id=?", (job_id,)).fetchone()
if row is None:
raise HTTPException(status_code=404, detail="Audiobook job not found")
return row
def job_payload(row: sqlite3.Row) -> dict:
total = row["total_characters"]
processed = row["processed_characters"]
progress = min(100, int(processed * 100 / total)) if total else 0
if row["status"] == "ready":
progress = 100
return {
"id": row["id"],
"status": row["status"],
"stage": row["stage"],
"progress": progress,
"processedCharacters": processed,
"totalCharacters": total,
"currentChapter": row["current_chapter"],
"durationMs": row["duration_ms"],
"chapters": json.loads(row["chapters_json"] or "[]"),
"error": row["error_message"],
"createdAt": row["created_at"],
"updatedAt": row["updated_at"],
}
@app.get("/health")
def health() -> dict:
return {
"status": "ok",
"workerMode": "lazy-model",
"activeJobId": worker_state["activeJobId"],
"modelLoaded": worker_state["modelLoaded"],
}
@app.post("/v1/audiobooks", dependencies=[Depends(require_token)])
async def create_audiobook(
book: Annotated[UploadFile, File()],
title: Annotated[str, Form()],
author: Annotated[str, Form()] = "",
) -> dict:
extension = Path(book.filename or "book.epub").suffix.lower()
if extension not in {".epub", ".fb2"}:
raise HTTPException(status_code=400, detail="Only EPUB and FB2 are supported")
job_id = uuid.uuid4().hex
job_root = DATA_ROOT / job_id
job_root.mkdir(parents=True)
input_path = job_root / f"source{extension}"
received = 0
try:
with input_path.open("wb") as output:
while chunk := await book.read(1024 * 1024):
received += len(chunk)
if received > MAX_UPLOAD_BYTES:
raise HTTPException(status_code=413, detail="Book file is too large")
output.write(chunk)
except Exception:
shutil.rmtree(job_root, ignore_errors=True)
raise
timestamp = now_ms()
with database() as connection:
connection.execute(
"""
INSERT INTO jobs (
id,title,author,source_name,input_path,output_path,status,stage,created_at,updated_at
) VALUES (?,?,?,?,?,?,?,?,?,?)
""",
(
job_id,
title.strip() or Path(book.filename or "Книга").stem,
author.strip(),
book.filename or input_path.name,
str(input_path),
str(job_root / "audiobook.m4a"),
"queued",
"queued",
timestamp,
timestamp,
),
)
with queue_condition:
queued_jobs.append(job_id)
queue_condition.notify()
return job_payload(get_job(job_id))
@app.get("/v1/audiobooks/{job_id}", dependencies=[Depends(require_token)])
def audiobook_status(job_id: str) -> dict:
return job_payload(get_job(job_id))
@app.get("/v1/audiobooks/{job_id}/file", dependencies=[Depends(require_token)])
def audiobook_file(job_id: str) -> FileResponse:
row = get_job(job_id)
output = Path(row["output_path"])
if row["status"] != "ready" or not output.is_file():
raise HTTPException(status_code=409, detail="Audiobook is not ready")
safe_title = re.sub(r"[^0-9A-Za-zА-Яа-яЁё._ -]+", "_", row["title"]).strip() or "audiobook"
return FileResponse(output, media_type="audio/mp4", filename=f"{safe_title}.m4a")
@app.delete("/v1/audiobooks/{job_id}", dependencies=[Depends(require_token)])
def cancel_or_delete(job_id: str) -> dict:
row = get_job(job_id)
if row["status"] == "queued":
with queue_condition:
queued_jobs[:] = [queued_id for queued_id in queued_jobs if queued_id != job_id]
delete_job(job_id, Path(row["input_path"]).parent)
return {"status": "deleted"}
if row["status"] in {"extracting", "synthesizing", "encoding"}:
with database() as connection:
connection.execute(
"UPDATE jobs SET cancel_requested=1, stage='cancelling', updated_at=? WHERE id=?",
(now_ms(), job_id),
)
return {"status": "cancelling"}
delete_job(job_id, Path(row["input_path"]).parent)
return {"status": "deleted"}
def delete_job(job_id: str, job_root: Path) -> None:
shutil.rmtree(job_root, ignore_errors=True)
with database() as connection:
connection.execute("DELETE FROM jobs WHERE id=?", (job_id,))
def finish_cancellation(job_id: str, job_root: Path) -> None:
update_job(job_id, status="cancelled", stage="cancelled")
delete_job(job_id, job_root)
def local_name(tag: str) -> str:
return tag.rsplit("}", 1)[-1].lower()
def clean_text(value: str) -> str:
value = html.unescape(re.sub(r"<[^>]+>", " ", value))
value = value.replace("\u00a0", " ")
return re.sub(r"\s+", " ", value).strip()
def extract_epub(path: Path) -> list[tuple[str, str]]:
sections: list[tuple[str, str]] = []
with zipfile.ZipFile(path) as archive:
container = ElementTree.fromstring(archive.read("META-INF/container.xml"))
rootfile = next(node for node in container.iter() if local_name(node.tag) == "rootfile")
opf_path = rootfile.attrib["full-path"]
opf = ElementTree.fromstring(archive.read(opf_path))
manifest = {
node.attrib["id"]: node.attrib["href"]
for node in opf.iter()
if local_name(node.tag) == "item" and "id" in node.attrib and "href" in node.attrib
}
spine = [
node.attrib["idref"]
for node in opf.iter()
if local_name(node.tag) == "itemref" and "idref" in node.attrib
]
base = PurePosixPath(opf_path).parent
for index, item_id in enumerate(spine, start=1):
href = manifest.get(item_id)
if not href:
continue
entry = str(base / href.split("#", 1)[0])
raw = archive.read(entry).decode("utf-8", errors="replace")
heading_match = re.search(r"<h[1-3]\b[^>]*>(.*?)</h[1-3]>", raw, re.I | re.S)
title = clean_text(heading_match.group(1)) if heading_match else f"Раздел {index}"
paragraphs = [clean_text(match) for match in re.findall(r"<p\b[^>]*>(.*?)</p>", raw, re.I | re.S)]
text = "\n".join(paragraph for paragraph in paragraphs if paragraph)
if text:
sections.append((title, text))
return sections
def element_text_without_nested_sections(element: ElementTree.Element) -> str:
parts: list[str] = []
if element.text:
parts.append(element.text)
for child in element:
if local_name(child.tag) != "section":
parts.append(" ".join(child.itertext()))
if child.tail:
parts.append(child.tail)
return clean_text(" ".join(parts))
def extract_fb2(path: Path) -> list[tuple[str, str]]:
root = ElementTree.parse(path).getroot()
sections: list[tuple[str, str]] = []
for section in root.iter():
if local_name(section.tag) != "section":
continue
title_element = next((child for child in section if local_name(child.tag) == "title"), None)
title = clean_text(" ".join(title_element.itertext())) if title_element is not None else ""
text = element_text_without_nested_sections(section)
if text:
sections.append((title or f"Раздел {len(sections) + 1}", text))
return sections
def normalize_numbers(text: str) -> str:
def replace(match: re.Match[str]) -> str:
value = match.group(0)
try:
return num2words(int(value), lang="ru")
except (ValueError, OverflowError):
return value
return re.sub(r"(?<![\w+])\d{1,12}(?!\w)", replace, text)
def split_chunks(sections: list[tuple[str, str]], limit: int = 520) -> list[dict]:
chunks: list[dict] = []
for chapter, text in sections:
sentences = re.split(r"(?<=[.!?…])\s+|\n+", text)
current = ""
for sentence in sentences:
sentence = normalize_numbers(sentence.strip())
if not sentence or not re.search(r"[А-Яа-яЁё]", sentence):
continue
if len(sentence) > limit:
pieces = re.split(r"(?<=[,;:])\s+", sentence)
else:
pieces = [sentence]
for piece in pieces:
if current and len(current) + 1 + len(piece) > limit:
chunks.append({"chapter": chapter, "text": current})
current = piece
else:
current = f"{current} {piece}".strip()
if current:
chunks.append({"chapter": chapter, "text": current})
return chunks
def update_job(job_id: str, **values: object) -> None:
values["updated_at"] = now_ms()
assignments = ",".join(f"{key}=?" for key in values)
with database() as connection:
connection.execute(
f"UPDATE jobs SET {assignments} WHERE id=?",
(*values.values(), job_id),
)
def cancellation_requested(job_id: str) -> bool:
with database() as connection:
row = connection.execute("SELECT cancel_requested FROM jobs WHERE id=?", (job_id,)).fetchone()
return row is None or bool(row["cancel_requested"])
def load_model(device_id: int) -> "Qwen3TTSModel":
import torch
from qwen_tts import Qwen3TTSModel
if not torch.cuda.is_available():
raise RuntimeError("CUDA is unavailable")
torch.set_float32_matmul_precision("high")
model = Qwen3TTSModel.from_pretrained(
MODEL_ID,
device_map=f"cuda:{device_id}",
dtype=torch.bfloat16,
attn_implementation="sdpa",
)
return model
def load_models() -> list["Qwen3TTSModel"]:
if not GPU_IDS:
raise RuntimeError("No Qwen GPU IDs are configured")
models = [load_model(device_id) for device_id in GPU_IDS]
worker_state["modelLoaded"] = True
return models
def generate_custom_voice_with_metrics(
model: Any,
batch_chunks: list[dict],
device_id: int,
) -> tuple[list[Any], int]:
"""Measure Qwen talker and codec stages without changing generated audio."""
import torch
timings: dict[str, float] = {}
original_generate = model.model.generate
speech_tokenizer = model.model.speech_tokenizer
original_decode = speech_tokenizer.decode
def synchronize() -> None:
if torch.cuda.is_available():
torch.cuda.synchronize(device_id)
def timed_generate(*args: Any, **kwargs: Any) -> Any:
synchronize()
started = time.perf_counter()
try:
return original_generate(*args, **kwargs)
finally:
synchronize()
timings["talkerGenerateSeconds"] = time.perf_counter() - started
def timed_decode(*args: Any, **kwargs: Any) -> Any:
synchronize()
started = time.perf_counter()
try:
return original_decode(*args, **kwargs)
finally:
synchronize()
timings["codecDecodeSeconds"] = time.perf_counter() - started
model.model.generate = timed_generate
speech_tokenizer.decode = timed_decode
started = time.perf_counter()
try:
wavs, sample_rate = model.generate_custom_voice(
text=[chunk["text"] for chunk in batch_chunks],
language=["Russian"] * len(batch_chunks),
speaker=[SPEAKER] * len(batch_chunks),
instruct=[VOICE_INSTRUCTION] * len(batch_chunks),
)
synchronize()
finally:
model.model.generate = original_generate
speech_tokenizer.decode = original_decode
total_seconds = time.perf_counter() - started
talker_seconds = timings.get("talkerGenerateSeconds", 0.0)
codec_seconds = timings.get("codecDecodeSeconds", 0.0)
record = {
"timestampMs": now_ms(),
"batchSize": len(batch_chunks),
"characters": sum(len(chunk["text"]) for chunk in batch_chunks),
"totalSeconds": round(total_seconds, 4),
"talkerGenerateSeconds": round(talker_seconds, 4),
"codecDecodeSeconds": round(codec_seconds, 4),
"wrapperSeconds": round(max(0.0, total_seconds - talker_seconds - codec_seconds), 4),
"cudaPeakAllocatedMiB": round(
torch.cuda.max_memory_allocated(device_id) / (1024 * 1024), 1
),
}
with PERFORMANCE_LOG.open("a", encoding="utf-8") as output:
output.write(json.dumps(record, ensure_ascii=False) + "\n")
return wavs, sample_rate
def unload_models(models: list[Any]) -> None:
if models:
models.clear()
import torch
gc.collect()
if torch.cuda.is_available():
for device_id in GPU_IDS:
torch.cuda.empty_cache()
else:
gc.collect()
worker_state["modelLoaded"] = False
def encode_m4a(chunk_files: list[Path], output: Path, job_root: Path) -> None:
concat = job_root / "concat.txt"
concat.write_text(
"\n".join(f"file '{path.as_posix()}'" for path in chunk_files),
encoding="utf-8",
)
command = [
imageio_ffmpeg.get_ffmpeg_exe(),
"-y",
"-f",
"concat",
"-safe",
"0",
"-i",
str(concat),
"-vn",
"-c:a",
"aac",
"-b:a",
"96k",
"-movflags",
"+faststart",
str(output),
]
completed = subprocess.run(command, capture_output=True, text=True, encoding="utf-8", errors="replace")
if completed.returncode != 0:
raise RuntimeError(completed.stderr[-2000:] or "FFmpeg failed")
def run_job(job_id: str) -> None:
row = get_job(job_id)
job_root = Path(row["input_path"]).parent
chunks_root = job_root / "chunks"
chunks_root.mkdir(exist_ok=True)
models: list[Any] = []
try:
if cancellation_requested(job_id):
finish_cancellation(job_id, job_root)
return
update_job(job_id, status="extracting", stage="extracting", error_message=None)
input_path = Path(row["input_path"])
sections = extract_epub(input_path) if input_path.suffix.lower() == ".epub" else extract_fb2(input_path)
chunks = split_chunks(sections)
if not chunks:
raise RuntimeError("В книге не найден русский текст для озвучивания")
total = sum(len(chunk["text"]) for chunk in chunks)
manifest_path = job_root / "chunks.json"
manifest_path.write_text(json.dumps(chunks, ensure_ascii=False, indent=2), encoding="utf-8")
update_job(job_id, status="synthesizing", stage="loading_model", total_characters=total)
if cancellation_requested(job_id):
finish_cancellation(job_id, job_root)
return
pause_ollama_for_audiobook()
models = load_models()
import torch
processed = 0
duration_ms = 0
chapter_markers: list[dict] = []
last_chapter: str | None = None
chunk_files: list[Path] = []
index = 0
while index < len(chunks):
if cancellation_requested(job_id):
finish_cancellation(job_id, job_root)
return
output = chunks_root / f"{index:06d}.wav"
completed_indices: list[int]
if output.is_file():
completed_indices = [index]
else:
batch_indices: list[int] = []
cursor = index
while cursor < len(chunks) and len(batch_indices) < len(models):
candidate = chunks_root / f"{cursor:06d}.wav"
if candidate.is_file():
break
batch_indices.append(cursor)
cursor += 1
with ThreadPoolExecutor(max_workers=len(batch_indices)) as executor:
futures = [
executor.submit(
generate_custom_voice_with_metrics,
model,
[chunks[batch_index]],
device_id,
)
for batch_index, model, device_id in zip(
batch_indices,
models[: len(batch_indices)],
GPU_IDS[: len(batch_indices)],
strict=True,
)
]
rendered = [future.result() for future in futures]
if cancellation_requested(job_id):
finish_cancellation(job_id, job_root)
return
for batch_index, (wavs, sample_rate) in zip(batch_indices, rendered, strict=True):
sf.write(
chunks_root / f"{batch_index:06d}.wav",
wavs[0],
sample_rate,
subtype="PCM_16",
)
completed_indices = batch_indices
for completed_index in completed_indices:
completed_chunk = chunks[completed_index]
completed_output = chunks_root / f"{completed_index:06d}.wav"
if completed_chunk["chapter"] != last_chapter:
chapter_markers.append({"title": completed_chunk["chapter"], "startMs": duration_ms})
last_chapter = completed_chunk["chapter"]
info = sf.info(completed_output)
duration_ms += round(info.frames * 1000 / info.samplerate)
chunk_files.append(completed_output)
processed += len(completed_chunk["text"])
update_job(
job_id,
status="synthesizing",
stage="synthesizing",
processed_characters=processed,
current_chapter=completed_chunk["chapter"],
duration_ms=duration_ms,
chapters_json=json.dumps(chapter_markers, ensure_ascii=False),
)
index = completed_indices[-1] + 1
unload_models(models)
models = []
if cancellation_requested(job_id):
finish_cancellation(job_id, job_root)
return
update_job(job_id, status="encoding", stage="encoding", current_chapter=None)
output = Path(row["output_path"])
encode_m4a(chunk_files, output, job_root)
if cancellation_requested(job_id):
finish_cancellation(job_id, job_root)
return
if not output.is_file() or output.stat().st_size == 0:
raise RuntimeError("Итоговый M4A-файл не создан")
update_job(
job_id,
status="ready",
stage="ready",
processed_characters=total,
current_chapter=None,
chapters_json=json.dumps(chapter_markers, ensure_ascii=False),
)
except Exception as error:
update_job(
job_id,
status="failed",
stage="failed",
error_message=f"{type(error).__name__}: {error}",
)
finally:
unload_models(models)
def worker_loop() -> None:
while True:
with queue_condition:
while not queued_jobs:
queue_condition.wait()
job_id = queued_jobs.pop(0)
worker_state["activeJobId"] = job_id
try:
try:
run_job(job_id)
except HTTPException as error:
if error.status_code != 404:
raise
finally:
worker_state["activeJobId"] = None
# Qwen/Triton can retain a CUDA context after Python references are
# released. Let systemd start a clean idle receiver so CMP VRAM is
# fully available between audiobook requests. Unfinished jobs are
# restored from SQLite by initialize_database() after restart.
os._exit(0)
initialize_database()
threading.Thread(target=worker_loop, name="audiobook-worker", daemon=True).start()