[Qwen3TTS] [TTS] [Feat] Refactor voice cache manager (#2108)
Signed-off-by: JuanPZuluaga <juanz9312@gmal.com> Signed-off-by: yiliu30 <yi4.liu@intel.com> Signed-off-by: gcanlin <canlinguosdu@gmail.com> Signed-off-by: Binh Tang <tangbinhna@gmail.com> Signed-off-by: Binh Tang <binht@netflix.com> Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com> Signed-off-by: Rein Yang <ruiruyang2@gmail.com> Signed-off-by: CHEN <116010019@link.cuhk.edu.cn> Signed-off-by: vraiti <vraiti@redhat.com> Signed-off-by: Songrui625 <songrui625@gmail.com> Signed-off-by: Lidang Jiang <lidangjiang@gmail.com> Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com> Signed-off-by: Alex Brooks <albrooks@redhat.com> Co-authored-by: JuanPZuluaga <juanz9312@gmal.com> Co-authored-by: Yi Liu <yi4.liu@intel.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com> Co-authored-by: Canlin Guo <canlinguosdu@gmail.com> Co-authored-by: Binh Tang <tangbinhna@gmail.com> Co-authored-by: Binh Tang <binht@netflix.com> Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com> Co-authored-by: rein yang <73573651+R2-Y@users.noreply.github.com> Co-authored-by: zhumingjue138 <zhumingjue@huawei.com> Co-authored-by: ChenWenjing <54166744+Shirley125@users.noreply.github.com> Co-authored-by: vraiti <vraiti@redhat.com> Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com> Co-authored-by: Sy03 <1370724210@qq.com> Co-authored-by: chickeyton <ngton2014@gmail.com> Co-authored-by: Jerry Song <46962917+Songrui625@users.noreply.github.com> Co-authored-by: Lidang Jiang <119769478+Lidang-Jiang@users.noreply.github.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: Alex Brooks <albrooks@redhat.com> Co-authored-by: linyueqian <linyueqian@outlook.com> Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
This commit is contained in:
11 files changed
+442
-614
No files matched your search
@@ -0,0 +1,89 @@
|
||||
"""In-memory LRU cache for voice extraction artifacts.
|
||||
|
||||
Keyed by voice name + extraction mode (e.g. ``"alice:icl"``).
|
||||
Only named voices are cached; inline ``ref_audio`` without a voice
|
||||
name is not cached.
|
||||
|
||||
Usage::
|
||||
|
||||
key = VoiceEmbeddingCache.make_cache_key("alice", xvec_only=False)
|
||||
cached = cache.get(key)
|
||||
if cached is None:
|
||||
# ... extract ...
|
||||
cache.put(key, {"artifact": result})
|
||||
"""
|
||||
|
||||
import os
|
||||
import threading
|
||||
from collections import OrderedDict
|
||||
from typing import Any
|
||||
|
||||
from vllm.logger import init_logger
|
||||
|
||||
logger = init_logger(__name__)
|
||||
|
||||
_DEFAULT_MAX_ENTRIES = 128
|
||||
|
||||
|
||||
class VoiceEmbeddingCache:
|
||||
"""LRU cache for voice extraction outputs.
|
||||
|
||||
Each entry stores a ``dict[str, Any]`` whose contents are model-specific.
|
||||
Thread-safe via a lightweight ``threading.Lock``.
|
||||
"""
|
||||
|
||||
def __init__(self, max_entries: int | None = None):
|
||||
if max_entries is None:
|
||||
max_entries = int(os.environ.get("VOICE_CACHE_MAX_ENTRIES", _DEFAULT_MAX_ENTRIES))
|
||||
self._cache: OrderedDict[str, dict[str, Any]] = OrderedDict()
|
||||
self._max_entries = max_entries
|
||||
self._lock = threading.Lock()
|
||||
self._hits = 0
|
||||
self._misses = 0
|
||||
logger.info("Voice embedding cache initialized (max_entries=%d)", max_entries)
|
||||
|
||||
@staticmethod
|
||||
def make_cache_key(voice_name: str, xvec_only: bool, created_at: float = 0.0) -> str:
|
||||
"""Build a cache key from a voice name, upload timestamp, and extraction mode.
|
||||
|
||||
Args:
|
||||
voice_name: The speaker/voice name (case-insensitive, lowered
|
||||
by the caller).
|
||||
xvec_only: True for speaker-embedding-only mode, False for
|
||||
ICL mode (speaker embedding + ref_code).
|
||||
created_at: Upload timestamp from metadata. Prevents stale cache
|
||||
hits after a voice is deleted and re-uploaded with the same
|
||||
name but different audio.
|
||||
"""
|
||||
mode = "xvec" if xvec_only else "icl"
|
||||
return f"{voice_name}:{created_at:.6f}:{mode}"
|
||||
|
||||
def get(self, key: str) -> dict[str, Any] | None:
|
||||
"""Return cached artifacts or ``None`` on miss. Promotes to MRU on hit."""
|
||||
with self._lock:
|
||||
if key in self._cache:
|
||||
self._cache.move_to_end(key)
|
||||
self._hits += 1
|
||||
logger.debug("Voice cache HIT (key=%s, hits=%d)", key, self._hits)
|
||||
return self._cache[key]
|
||||
self._misses += 1
|
||||
return None
|
||||
|
||||
def put(self, key: str, artifacts: dict[str, Any]) -> None:
|
||||
"""Store *artifacts* under *key*, evicting the LRU entry if full."""
|
||||
with self._lock:
|
||||
self._cache[key] = artifacts
|
||||
self._cache.move_to_end(key)
|
||||
while len(self._cache) > self._max_entries:
|
||||
evicted_key, _ = self._cache.popitem(last=False)
|
||||
logger.debug("Voice cache EVICT (key=%s)", evicted_key)
|
||||
|
||||
def stats(self) -> dict[str, int]:
|
||||
"""Return cache statistics."""
|
||||
with self._lock:
|
||||
return {
|
||||
"entries": len(self._cache),
|
||||
"max_entries": self._max_entries,
|
||||
"hits": self._hits,
|
||||
"misses": self._misses,
|
||||
}
|
||||
Reference in new issue
Block a user