feat(xinference): set response_format to verbose_json (#2142)

* feat(xinference): set response_format to verbose_json

修改语音转文字默认响应格式为verbose_json

* Update manifest.yaml

* Apply suggestion from @gemini-code-assist[bot]

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

---------

Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

Author: 3 people

models/xinference/manifest.yaml

@@ -32,4 +32,4 @@ resource:
     tool:
       enabled: true
 type: plugin
-version: 0.0.7
+version: 0.0.8

models/xinference/models/speech2text/speech2text.py

@@ -80,7 +80,7 @@ def _speech2text_invoke(
         file: IO[bytes],
         language: Optional[str] = None,
         prompt: Optional[str] = None,
-        response_format: Optional[str] = "json",
+        response_format: Optional[str] = "verbose_json",
         temperature: Optional[float] = 0,
     ) -> str:
         """