修复后端声纹模型加载失败问题
parent
fdd9ae20a4
commit
400068692e
|
|
@ -33,12 +33,21 @@ def _get_model() -> Any:
|
|||
kwargs = dict(settings.FUNASR_AUTOMODEL_KWARGS)
|
||||
kwargs["disable_update"] = settings.FUNASR_DISABLE_UPDATE
|
||||
logger.info(
|
||||
"Loading FunASR realtime speaker model: model=%s device=%s disable_update=%s",
|
||||
"Loading FunASR realtime speaker model: model_id=%s model_path=%s device=%s disable_update=%s",
|
||||
settings.REALTIME_SV_MODEL,
|
||||
model_path,
|
||||
device,
|
||||
settings.FUNASR_DISABLE_UPDATE,
|
||||
)
|
||||
_model = AutoModel(model=model_path, device=device, **kwargs)
|
||||
# Keep the registered ModelScope ID as ``model`` so FunASR can
|
||||
# resolve ERes2NetV2's model class; pass the local cache path
|
||||
# separately to load its config and weights without downloading.
|
||||
_model = AutoModel(
|
||||
model=settings.REALTIME_SV_MODEL,
|
||||
model_path=model_path,
|
||||
device=device,
|
||||
**kwargs,
|
||||
)
|
||||
logger.info("FunASR realtime speaker model loaded: %s", model_path)
|
||||
return _model
|
||||
|
||||
|
|
|
|||
|
|
@ -4,6 +4,7 @@
|
|||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import threading
|
||||
from typing import Any, Dict, List, Optional, Tuple
|
||||
|
||||
import numpy as np
|
||||
|
|
@ -17,6 +18,8 @@ from app.services.asr.funasr_speaker import extract_realtime_speaker_embeddings
|
|||
from app.services.speaker_registry import get_speaker_registry_service
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
_funasr_embedding_fallback_logged = False
|
||||
_funasr_embedding_fallback_log_lock = threading.Lock()
|
||||
|
||||
|
||||
class RealtimeSpeakerClusterer:
|
||||
|
|
@ -291,10 +294,35 @@ class RealtimeSpeakerClusterer:
|
|||
|
||||
# 与 FunASR 实时跟踪器保持一致:整批声纹窗口通过 AutoModel.generate
|
||||
# 提取,确保先执行 ERes2Net 所需的音频特征预处理,再进入模型。
|
||||
embeddings = await run_sync(
|
||||
extract_realtime_speaker_embeddings,
|
||||
[item["audio"] for item in chunk_items],
|
||||
)
|
||||
try:
|
||||
embeddings = await run_sync(
|
||||
extract_realtime_speaker_embeddings,
|
||||
[item["audio"] for item in chunk_items],
|
||||
)
|
||||
except Exception:
|
||||
# Keep speaker IDs and live turn cuts available if this checkpoint
|
||||
# cannot be loaded through FunASR AutoModel in the deployed runtime.
|
||||
# The warning makes the fallback visible so it is not mistaken for
|
||||
# a fully FunASR-aligned embedding path.
|
||||
global _funasr_embedding_fallback_logged
|
||||
with _funasr_embedding_fallback_log_lock:
|
||||
if not _funasr_embedding_fallback_logged:
|
||||
logger.exception(
|
||||
"FunASR realtime speaker embedding failed; falling back to the "
|
||||
"configured ModelScope speaker model for this batch"
|
||||
)
|
||||
_funasr_embedding_fallback_logged = True
|
||||
registry = get_speaker_registry_service()
|
||||
embeddings = [
|
||||
await run_sync(
|
||||
registry.extract_embedding_from_audio,
|
||||
item["audio"],
|
||||
16000,
|
||||
model_id=settings.REALTIME_SV_MODEL,
|
||||
model_revision=settings.REALTIME_SV_MODEL_REVISION or None,
|
||||
)
|
||||
for item in chunk_items
|
||||
]
|
||||
results: List[Dict[str, Any]] = []
|
||||
for item, embedding in zip(chunk_items, embeddings):
|
||||
results.append(
|
||||
|
|
|
|||
Loading…
Reference in New Issue