ChatTTS下载好后不能运行，其它的模型都可以起启

[cq134cq]

System Info / 系統信息

:\soft\xxx>conda env config vars set XINFERENCE_HOME=c:\soft\models

C:\soft\xxx>conda activate c:\soft\xxx

(c:\soft\xxx) C:\soft\xxx>xinference-local --host 10.0.100.57 --port 9997

Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece？

• docker / docker
• pip install / 通过 pip install 安装
• installation from source / 从源码安装

Version info / 版本信息

1.2.0

The command used to start Xinference / 用以启动 xinference 的命令

c:\soft\xxx>conda env config vars set XINFERENCE_HOME=c:\soft\models

C:\soft\xxx>conda activate c:\soft\xxx

(c:\soft\xxx) C:\soft\xxx>xinference-local --host 10.0.100.57 --port 9997

Reproduction / 复现过程

(c:\soft\xxx) C:\soft\xxx>xinference-local --host 10.0.100.57 --port 9997
2025-01-23 17:11:12,381 xinference.core.supervisor 6008 INFO Xinference supervisor 10.0.100.57:17503 started
2025-01-23 17:11:12,403 xinference.core.worker 6008 INFO Starting metrics export server at 10.0.100.57:None
2025-01-23 17:11:12,404 xinference.core.worker 6008 INFO Checking metrics export server...
2025-01-23 17:11:14,001 xinference.core.worker 6008 INFO Metrics server is started at: http://10.0.100.57:58705
2025-01-23 17:11:14,001 xinference.core.worker 6008 INFO Purge cache directory: c:\soft\models\cache
2025-01-23 17:11:14,003 xinference.core.worker 6008 INFO Connected to supervisor as a fresh worker
2025-01-23 17:11:14,023 xinference.core.worker 6008 INFO Xinference worker 10.0.100.57:17503 started
2025-01-23 17:11:15,021 xinference.api.restful_api 11396 INFO Starting Xinference at endpoint: http://10.0.100.57:9997
2025-01-23 17:11:15,110 uvicorn.error 11396 INFO Uvicorn running on http://10.0.100.57:9997 (Press CTRL+C to quit)
2025-01-23 17:11:27,671 xinference.core.worker 6008 INFO [request 06dd7fe1-d96a-11ef-9c9f-047c1678e4a5] Enter launch_builtin_model, args: <xinference.core.worker.WorkerActor object at 0x00000249D7BA44F0>, kwargs: model_uid=ChatTTS-0,model_name=ChatTTS,model_size_in_billions=None,model_format=None,quantization=None,model_engine=None,model_type=audio,n_gpu=auto,request_limits=None,peft_model_config=None,gpu_idx=None,download_hub=None,model_path=None,xavier_config=None
2025-01-23 17:11:27,998 xinference.model.utils 6008 INFO Use model cache from a different hub.
2025-01-23 17:11:31,485 xinference.core.model 5616 INFO Start requests handler.
2025-01-23 17:11:32,296 xinference.model.audio.chattts 5616 INFO Load ChatTTS model with kwargs: {}
check models in custom path C:\soft\models\cache\ChatTTS failed.
2025-01-23 17:11:32,298 xinference.core.worker 6008 ERROR Failed to load model ChatTTS-0
Traceback (most recent call last):
File "c:\soft\xxx\lib\site-packages\xinference\core\worker.py", line 908, in launch_builtin_model
await model_ref.load()
File "c:\soft\xxx\lib\site-packages\xoscar\backends\context.py", line 231, in send
return self._process_result_message(result)
File "c:\soft\xxx\lib\site-packages\xoscar\backends\context.py", line 102, in _process_result_message
raise message.as_instanceof_cause()
File "c:\soft\xxx\lib\site-packages\xoscar\backends\pool.py", line 667, in send
result = await self._run_coro(message.message_id, coro)
File "c:\soft\xxx\lib\site-packages\xoscar\backends\pool.py", line 370, in _run_coro
return await coro
File "c:\soft\xxx\lib\site-packages\xoscar\api.py", line 384, in on_receive
return await super().on_receive(message) # type: ignore
File "xoscar\core.pyx", line 558, in on_receive
raise ex
File "xoscar\core.pyx", line 520, in xoscar.core._BaseActor.on_receive
async with self._lock:
File "xoscar\core.pyx", line 521, in xoscar.core._BaseActor.on_receive
with debug_async_timeout('actor_lock_timeout',
File "xoscar\core.pyx", line 526, in xoscar.core._BaseActor.on_receive
result = await result
File "c:\soft\xxx\lib\site-packages\xinference\core\model.py", line 455, in load
self._model.load()
File "c:\soft\xxx\lib\site-packages\xinference\model\audio\chattts.py", line 61, in load
raise Exception(f"The ChatTTS model is not correct: {self._model_path}")
Exception: [address=10.0.100.57:58719, pid=5616] The ChatTTS model is not correct: C:\soft\models\cache\ChatTTS
2025-01-23 17:11:32,344 xinference.core.worker 6008 ERROR [request 06dd7fe1-d96a-11ef-9c9f-047c1678e4a5] Leave launch_builtin_model, error: [address=10.0.100.57:58719, pid=5616] The ChatTTS model is not correct: C:\soft\models\cache\ChatTTS, elapsed time: 4 s
Traceback (most recent call last):
File "c:\soft\xxx\lib\site-packages\xinference\core\utils.py", line 94, in wrapped
ret = await func(*args, **kwargs)
File "c:\soft\xxx\lib\site-packages\xinference\core\worker.py", line 908, in launch_builtin_model
await model_ref.load()
File "c:\soft\xxx\lib\site-packages\xoscar\backends\context.py", line 231, in send
return self._process_result_message(result)
File "c:\soft\xxx\lib\site-packages\xoscar\backends\context.py", line 102, in _process_result_message
raise message.as_instanceof_cause()
File "c:\soft\xxx\lib\site-packages\xoscar\backends\pool.py", line 667, in send
result = await self._run_coro(message.message_id, coro)
File "c:\soft\xxx\lib\site-packages\xoscar\backends\pool.py", line 370, in _run_coro
return await coro
File "c:\soft\xxx\lib\site-packages\xoscar\api.py", line 384, in on_receive
return await super().on_receive(message) # type: ignore
File "xoscar\core.pyx", line 558, in on_receive
raise ex
File "xoscar\core.pyx", line 520, in xoscar.core._BaseActor.on_receive
async with self._lock:
File "xoscar\core.pyx", line 521, in xoscar.core._BaseActor.on_receive
with debug_async_timeout('actor_lock_timeout',
File "xoscar\core.pyx", line 526, in xoscar.core._BaseActor.on_receive
result = await result
File "c:\soft\xxx\lib\site-packages\xinference\core\model.py", line 455, in load
self._model.load()
File "c:\soft\xxx\lib\site-packages\xinference\model\audio\chattts.py", line 61, in load
raise Exception(f"The ChatTTS model is not correct: {self._model_path}")
Exception: [address=10.0.100.57:58719, pid=5616] The ChatTTS model is not correct: C:\soft\models\cache\ChatTTS
2025-01-23 17:11:32,347 xinference.api.restful_api 11396 ERROR [address=10.0.100.57:58719, pid=5616] The ChatTTS model is not correct: C:\soft\models\cache\ChatTTS
Traceback (most recent call last):
File "c:\soft\xxx\lib\site-packages\xinference\api\restful_api.py", line 1002, in launch_model
model_uid = await (await self._get_supervisor_ref()).launch_builtin_model(
File "c:\soft\xxx\lib\site-packages\xoscar\backends\context.py", line 231, in send
return self._process_result_message(result)
File "c:\soft\xxx\lib\site-packages\xoscar\backends\context.py", line 102, in _process_result_message
raise message.as_instanceof_cause()
File "c:\soft\xxx\lib\site-packages\xoscar\backends\pool.py", line 667, in send
result = await self._run_coro(message.message_id, coro)
File "c:\soft\xxx\lib\site-packages\xoscar\backends\pool.py", line 370, in _run_coro
return await coro
File "c:\soft\xxx\lib\site-packages\xoscar\api.py", line 384, in on_receive
return await super().on_receive(message) # type: ignore
File "xoscar\core.pyx", line 558, in on_receive
raise ex
File "xoscar\core.pyx", line 520, in xoscar.core._BaseActor.on_receive
async with self._lock:
File "xoscar\core.pyx", line 521, in xoscar.core._BaseActor.on_receive
with debug_async_timeout('actor_lock_timeout',
File "xoscar\core.pyx", line 526, in xoscar.core._BaseActor.on_receive
result = await result
File "c:\soft\xxx\lib\site-packages\xinference\core\supervisor.py", line 1103, in launch_builtin_model
await _launch_model()
File "c:\soft\xxx\lib\site-packages\xinference\core\supervisor.py", line 1046, in _launch_model
subpool_address = await _launch_one_model(
File "c:\soft\xxx\lib\site-packages\xinference\core\supervisor.py", line 1003, in _launch_one_model
subpool_address = await worker_ref.launch_builtin_model(
File "xoscar\core.pyx", line 284, in __pyx_actor_method_wrapper
async with lock:
File "xoscar\core.pyx", line 287, in xoscar.core.__pyx_actor_method_wrapper
result = await result
File "c:\soft\xxx\lib\site-packages\xinference\core\utils.py", line 94, in wrapped
ret = await func(*args, **kwargs)
File "c:\soft\xxx\lib\site-packages\xinference\core\worker.py", line 908, in launch_builtin_model
await model_ref.load()
File "c:\soft\xxx\lib\site-packages\xoscar\backends\context.py", line 231, in send
return self._process_result_message(result)
File "c:\soft\xxx\lib\site-packages\xoscar\backends\context.py", line 102, in _process_result_message
raise message.as_instanceof_cause()
File "c:\soft\xxx\lib\site-packages\xoscar\backends\pool.py", line 667, in send
result = await self._run_coro(message.message_id, coro)
File "c:\soft\xxx\lib\site-packages\xoscar\backends\pool.py", line 370, in _run_coro
return await coro
File "c:\soft\xxx\lib\site-packages\xoscar\api.py", line 384, in on_receive
return await super().on_receive(message) # type: ignore
File "xoscar\core.pyx", line 558, in on_receive
raise ex
File "xoscar\core.pyx", line 520, in xoscar.core._BaseActor.on_receive
async with self._lock:
File "xoscar\core.pyx", line 521, in xoscar.core._BaseActor.on_receive
with debug_async_timeout('actor_lock_timeout',
File "xoscar\core.pyx", line 526, in xoscar.core._BaseActor.on_receive
result = await result
File "c:\soft\xxx\lib\site-packages\xinference\core\model.py", line 455, in load
self._model.load()
File "c:\soft\xxx\lib\site-packages\xinference\model\audio\chattts.py", line 61, in load
raise Exception(f"The ChatTTS model is not correct: {self._model_path}")
Exception: [address=10.0.100.57:58719, pid=5616] The ChatTTS model is not correct: C:\soft\models\cache\ChatTTS

Expected behavior / 期待表现

可以正常运行

[cq134cq]

[cq134cq]

[qinxuye]

@codingl2k1 can you help?

[cq134cq]

can you help?

或者告诉我问题出在那里