Merge pull request #2747 from xinnan-tech/py_asr_doubao_stream

豆包ASR流式自定义语句停止时长

main/manager-api/src/main/resources/db/changelog/202512221117.sql

@@ -0,0 +1,10 @@
+-- 更新豆包流式ASR供应器，增加end_window_size配置
+delete from `ai_model_provider` where id = 'SYSTEM_ASR_DoubaoStreamASR';
+INSERT INTO `ai_model_provider` (`id`, `model_type`, `provider_code`, `name`, `fields`, `sort`, `creator`, `create_date`, `updater`, `update_date`) VALUES
+('SYSTEM_ASR_DoubaoStreamASR', 'ASR', 'doubao_stream', '火山引擎语音识别(流式)', '[{"key":"appid","label":"应用ID","type":"string"},{"key":"access_token","label":"访问令牌","type":"string"},{"key":"cluster","label":"集群","type":"string"},{"key":"boosting_table_name","label":"热词文件名称","type":"string"},{"key":"correct_table_name","label":"替换词文件名称","type":"string"},{"key":"output_dir","label":"输出目录","type":"string"},{"key":"end_window_size","label":"静音判定时长(ms)","type":"number"}]', 3, 1, NOW(), 1, NOW());
+
+
+-- 更新豆包流式ASR模型配置，增加end_window_size默认值
+UPDATE `ai_model_config` SET
+`config_json` = JSON_SET(`config_json`, '$.end_window_size', 200)
+WHERE `id` = 'ASR_DoubaoStreamASR' AND JSON_EXTRACT(`config_json`, '$.end_window_size') IS NULL;

main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml

@@ -458,4 +458,11 @@ databaseChangeLog:
       changes:
         - sqlFile:
             encoding: utf8
-            path: classpath:db/changelog/202512192245.sql
+            path: classpath:db/changelog/202512192245.sql
+  - changeSet:
+      id: 202512221117
+      author: RanChen
+      changes:
+        - sqlFile:
+            encoding: utf8
+            path: classpath:db/changelog/202512221117.sql

main/xiaozhi-server/config.yaml

@@ -346,6 +346,8 @@ ASR:
     # 热词、替换词使用流程：https://www.volcengine.com/docs/6561/155738
     boosting_table_name: （选填）你的热词文件名称
     correct_table_name: （选填）你的替换词文件名称
+    # 静音判定时长(ms)，默认200ms
+    end_window_size: 200
     output_dir: tmp/
   TencentASR:
     # token申请地址：https://console.cloud.tencent.com/cam/capi

main/xiaozhi-server/core/providers/asr/doubao_stream.py

@@ -47,6 +47,8 @@ class ASRProvider(ASRProviderBase):
         self.channel = config.get("channel", 1)
         self.auth_method = config.get("auth_method", "token")
         self.secret = config.get("secret", "access_secret")
+        end_window_size = config.get("end_window_size")
+        self.end_window_size = int(end_window_size) if end_window_size else 200
 
     async def open_audio_channels(self, conn):
         await super().open_audio_channels(conn)
@@ -291,7 +293,7 @@ class ASRProvider(ASRProviderBase):
                 "sequence": 1,
                 "boosting_table_name": self.boosting_table_name,
                 "correct_table_name": self.correct_table_name,
-                "end_window_size": 200,
+                "end_window_size": self.end_window_size,
             },
             "audio": {
                 "format": self.format,