309a051038
数据库与模型：新增多版迁移（章节证据快照、对话血缘、记忆事实/时间线 lineage 等），把「成稿 ↔ 对话/记忆」的溯源信息落到表结构里。 业务链路：会话与 WS、回忆录/故事流水线、记忆写入与 enrichment 等跟着接上线索与快照；新增章节证据快照与评测侧 EvalTraceService 等模块，方便组评审用的证据包。 内部评测：自动化 run 与手工 memoir 评审共用可追溯证据；rubric/ judge 相关脚本与文档有配套调整。 app-eval-web：Memoir/实验详情里能展开看证据摘要与 evidence_trace（含对话轮次 id）；Vite 代理与 development.sh 注入的 API 端口与当前默认内部评测端口一致，避免改端口后页面连错服务。 工程杂项：GitHub Actions / 仓库说明有更新；各适配器与支付/配额/plan 等多处为小改动或跟随主改动的收尾；新增/扩充了?
79 lines
3.0 KiB
Python
79 lines
3.0 KiB
Python
"""Tencent Cloud ASR adapter — implements ASRProvider port."""
|
||
|
||
import asyncio
|
||
import base64
|
||
|
||
from app.core.logging import get_logger
|
||
from app.ports.asr import ASRTranscriptionError
|
||
|
||
logger = get_logger(__name__)
|
||
|
||
|
||
class TencentASRProvider:
|
||
def __init__(self, secret_id: str, secret_key: str):
|
||
self._secret_id = secret_id
|
||
self._secret_key = secret_key
|
||
self._client = None
|
||
|
||
def _get_client(self):
|
||
if self._client is not None:
|
||
return self._client
|
||
try:
|
||
from tencentcloud.asr.v20190614 import asr_client
|
||
from tencentcloud.common import credential
|
||
from tencentcloud.common.profile.client_profile import ClientProfile
|
||
from tencentcloud.common.profile.http_profile import HttpProfile
|
||
|
||
cred = credential.Credential(self._secret_id, self._secret_key)
|
||
http_profile = HttpProfile()
|
||
http_profile.endpoint = "asr.tencentcloudapi.com"
|
||
client_profile = ClientProfile()
|
||
client_profile.httpProfile = http_profile
|
||
self._client = asr_client.AsrClient(cred, "", client_profile)
|
||
return self._client
|
||
except Exception as e:
|
||
logger.error("Tencent ASR client init failed: {}", e)
|
||
return None
|
||
|
||
def ensure_ready(self) -> bool:
|
||
return bool(self._secret_id and self._secret_key and self._get_client())
|
||
|
||
async def transcribe(self, audio: bytes, format: str = "m4a") -> str:
|
||
client = self._get_client()
|
||
if not client:
|
||
raise ASRTranscriptionError(
|
||
"Tencent ASR client not initialized (check credentials)"
|
||
)
|
||
try:
|
||
from tencentcloud.asr.v20190614 import models
|
||
|
||
audio_base64 = base64.b64encode(audio).decode("utf-8")
|
||
req = models.SentenceRecognitionRequest()
|
||
req.EngSerViceType = "16k_zh"
|
||
req.SourceType = 1
|
||
# 小写；与文档一致。iOS 常见为 m4a(AAC) 容器，与 16k 引擎匹配
|
||
req.VoiceFormat = (format or "m4a").lower()
|
||
req.Data = audio_base64
|
||
req.DataLen = len(audio)
|
||
|
||
# 腾讯 SDK 为同步阻塞调用；放到线程池里避免卡住事件循环。
|
||
resp = await asyncio.to_thread(client.SentenceRecognition, req)
|
||
text = (resp.Result or "").strip()
|
||
if text:
|
||
return text
|
||
err = getattr(resp, "Error", None) or getattr(resp, "Message", None)
|
||
logger.warning(
|
||
"Tencent ASR empty Result, audio_len={} format={} err={}",
|
||
len(audio),
|
||
req.VoiceFormat,
|
||
err,
|
||
)
|
||
raise ASRTranscriptionError(
|
||
"Tencent ASR empty Result (check sample rate / format / audio)"
|
||
)
|
||
except ASRTranscriptionError:
|
||
raise
|
||
except Exception as e:
|
||
logger.error("Tencent ASR transcribe failed: {}", e, exc_info=True)
|
||
raise ASRTranscriptionError(f"Tencent ASR transcribe failed: {e!s}") from e
|