duixcom
Error: Error invoking remote method 'model/addModel': TypeError: SQLite3 can only bind numbers, strings, bigints, buffers, and null
heygem-tts | taskset: bad usage
heygem-tts | Try 'taskset --help' for more information.
heygem-tts | INFO:gjtts_server:加载自定义 姓名多音字 [/code/tools/text_norm/front_end/utils/name_polyphone.json]
heygem-gen-video | 2025-05-05 05:45:39,434 - cv2box - INFO - Use default multi mode: multi-thread, or you can set env 'CV_MULTI_MODE' to multi-process/torch-process
heygem-gen-video | [2025-05-05 05:45:39] [cv_logging.py[line:27]] [INFO] [Use default multi mode: multi-thread, or you can set env 'CV_MULTI_MODE' to multi-process/torch-process]
heygem-gen-video | [2025-05-05 05:45:41] [app_local.py[line:230]] [WARNING] [ -> 服务不进行注册]
heygem-gen-video | [2025-05-05 05:45:41] [app_local.py[line:231]] [INFO] [TransDhTask init]
heygem-tts | INFO: Started server process [1]
heygem-tts | INFO: Waiting for application startup.
heygem-tts | DEBUG:gjtts_server:语言类型 CN_EN
heygem-tts | DEBUG:gjtts_server:加载自定义 单位 [/code/tools/text_norm/front_end/normalize/config/units.json]
heygem-tts | DEBUG:gjtts_server:加载自定义 单位 [/code/tools/text_norm/front_end/normalize/config/units.json]
heygem-tts | DEBUG:gjtts_server:加载自定义 单位 [/code/tools/text_norm/front_end/normalize/config/units.json]
heygem-gen-video | [2025-05-05 05:45:45] [process.py[line:108]] [INFO] [>>> init_wh_process进程启动]
heygem-tts | 2025-05-05 05:45:46,865 - modelscope - WARNING - Using branch: master as version is unstable, use with caution
heygem-tts | 2025-05-05 05:45:50.243 | INFO | tools.server.model_manager:load_asr_model:77 - ASR model loaded.
heygem-gen-video | [2025-05-05 05:45:55] [process.py[line:108]] [INFO] [>>> 数字人图片处理进程启动]
heygem-tts | 2025-05-05 05:45:55.755 | INFO | tools.llama.generate:load_model:682 - Restored model from checkpoint
heygem-tts | 2025-05-05 05:45:55.756 | INFO | tools.llama.generate:load_model:688 - Using DualARTransformer
heygem-tts | 2025-05-05 05:45:55.771 | INFO | tools.server.model_manager:load_llama_model:102 - LLAMA model loaded.
heygem-tts | 2025-05-05 05:45:56.548 | INFO | tools.vqgan.inference:load_model:43 - Loaded model: <All keys matched successfully>
heygem-tts | 2025-05-05 05:45:56.548 | INFO | tools.server.model_manager:load_decoder_model:110 - Decoder model loaded.
heygem-tts | 2025-05-05 05:45:56.559 | INFO | tools.llama.generate:generate_long:789 - Encoded text: Hello world.
heygem-tts | 2025-05-05 05:45:56.559 | INFO | tools.llama.generate:generate_long:807 - Generating sentence 1/1 of sample 1/1
heygem-tts | 环境变量LOGGER_FILE_NAME不存在，使用自定义名称：fish
heygem-tts | 日志完整目录：/code/log/fish.log /code/log/fish_err.log
heygem-tts | funasr version: 1.2.6.
heygem-tts | Check update of funasr, and it would cost few times. You may disable it by set `disable_update=True` in AutoModel
heygem-tts | You are using the latest version of funasr-1.2.6
heygem-tts | Downloading Model from https://www.modelscope.cn to directory: /root/.cache/modelscope/hub/models/iic/SenseVoiceSmall
heygem-tts | None Hello world.
heygem-tts | Hello world.
heygem-gen-video | [2025-05-05 05:45:57] [app_local.py[line:233]] [INFO] [******************* TransDhServer服务启动 *******************]
heygem-gen-video | [2025-05-05 05:45:57] [app_local.py[line:235]] [INFO] [创建临时目录]
heygem-gen-video | [2025-05-05 05:45:57] [app_local.py[line:238]] [INFO] [创建结果目录]
heygem-gen-video | * Serving Flask app 'app_local'
heygem-gen-video | * Debug mode: off
heygem-gen-video | [2025-05-05 05:45:57] [_internal.py[line:97]] [INFO] [WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
heygem-gen-video | * Running on all addresses (0.0.0.0)
heygem-gen-video | * Running on http://127.0.0.1:8383
heygem-gen-video | * Running on http://172.21.0.2:8383]
heygem-gen-video | [2025-05-05 05:45:57] [_internal.py[line:97]] [INFO] [Press CTRL+C to quit]
3%|▎ | 27/1023 [00:01<01:09, 14.39it/s]
heygem-tts | 2025-05-05 05:45:58.930 | INFO | tools.llama.generate:generate_long:861 - Generated 29 tokens in 2.37 seconds, 12.26 tokens/sec
heygem-tts | 2025-05-05 05:45:58.931 | INFO | tools.llama.generate:generate_long:864 - Bandwidth achieved: 7.82 GB/s
heygem-tts | 2025-05-05 05:45:58.931 | INFO | tools.llama.generate:generate_long:869 - GPU Memory used: 2.81 GB
heygem-tts | 2025-05-05 05:45:58.932 | INFO | tools.inference_engine.vq_manager:decode_vq_tokens:20 - VQ features: torch.Size([8, 28])
heygem-tts | 2025-05-05 05:45:59.525 | INFO | tools.server.model_manager:warm_up:125 - Models warmed up.
heygem-tts | 2025-05-05 05:45:59.526 | INFO | __main__:initialize_app:88 - Startup done, listening server at http://0.0.0.0:8080
heygem-tts | INFO: Application startup complete.
heygem-tts | INFO: Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit)
heygem-tts | 2025-05-05 05:55:44.863 | INFO | tools.server.views_guiji:api_do_preprocess:144 - 收到训练请求：reference_audio='origin_audio/20250505135544510.wav' format='wav' lang='zh'
heygem-tts | 2025-05-05 05:55:44.864 | INFO | tools.server.views_guiji:build_tts_item:47 - 创建会话目录：/code/sessions/20250505/e158a12c373a4dd3905eba1e7e276f5a
heygem-tts | 2025-05-05 05:55:44.865 | INFO | tools.server.views_guiji:build_tts_item:52 - reference_audio不是url地址，本地路径为：/code/data/origin_audio/20250505135544510.wav
heygem-tts | 2025-05-05 05:55:44.866 | ERROR | tools.server.views_guiji:api_do_preprocess:167 - An error occurred: file not exists
heygem-tts | Stack trace:
heygem-tts | Traceback (most recent call last):
heygem-tts | File "/code/tools/server/views_guiji.py", line 151, in api_do_preprocess
heygem-tts | tts_item: TtsItem = build_tts_item(req)
heygem-tts | File "/code/tools/server/views_guiji.py", line 54, in build_tts_item
heygem-tts | raise Exception('file not exists')
heygem-tts | Exception: file not exists
heygem-tts |
heygem-tts | 2025-05-05 05:55:44.867 | INFO | tools.server.views_guiji:api_do_preprocess:170 - 训练返回结果：{'code': -1, 'msg': 'file not exists'}
heygem-tts | INFO: 172.21.0.1:53832 - "POST /v1/preprocess_and_tran HTTP/1.1" 200 OK
heygem-tts | 2025-05-05 05:55:55.811 | INFO | tools.server.views_guiji:api_do_preprocess:144 - 收到训练请求：reference_audio='origin_audio/20250505135555647.wav' format='wav' lang='zh'
heygem-tts | 2025-05-05 05:55:55.811 | INFO | tools.server.views_guiji:build_tts_item:47 - 创建会话目录：/code/sessions/20250505/7f62ff53a4fc4d8b8be0e90e19d2cbb1
heygem-tts | 2025-05-05 05:55:55.811 | INFO | tools.server.views_guiji:build_tts_item:52 - reference_audio不是url地址，本地路径为：/code/data/origin_audio/20250505135555647.wav
heygem-tts | 2025-05-05 05:55:55.812 | ERROR | tools.server.views_guiji:api_do_preprocess:167 - An error occurred: file not exists
heygem-tts | Stack trace:
heygem-tts | Traceback (most recent call last):
heygem-tts | File "/code/tools/server/views_guiji.py", line 151, in api_do_preprocess
heygem-tts | tts_item: TtsItem = build_tts_item(req)
heygem-tts | File "/code/tools/server/views_guiji.py", line 54, in build_tts_item
heygem-tts | raise Exception('file not exists')
heygem-tts | Exception: file not exists
heygem-tts |
heygem-tts | 2025-05-05 05:55:55.812 | INFO | tools.server.views_guiji:api_do_preprocess:170 - 训练返回结果：{'code': -1, 'msg': 'file not exists'}
heygem-tts | INFO: 172.21.0.1:44646 - "POST /v1/preprocess_and_tran HTTP/1.1" 200 OK
heygem-tts | 2025-05-05 05:57:08.951 | INFO | tools.server.views_guiji:api_do_preprocess:144 - 收到训练请求：reference_audio='origin_audio/20250505135708804.wav' format='wav' lang='zh'
heygem-tts | 2025-05-05 05:57:08.952 | INFO | tools.server.views_guiji:build_tts_item:47 - 创建会话目录：/code/sessions/20250505/1ed89bfcda444a2bb864c05b0fbb6ad7
heygem-tts | 2025-05-05 05:57:08.952 | INFO | tools.server.views_guiji:build_tts_item:52 - reference_audio不是url地址，本地路径为：/code/data/origin_audio/20250505135708804.wav
heygem-tts | 2025-05-05 05:57:08.952 | ERROR | tools.server.views_guiji:api_do_preprocess:167 - An error occurred: file not exists
heygem-tts | Stack trace:
heygem-tts | Traceback (most recent call last):
heygem-tts | File "/code/tools/server/views_guiji.py", line 151, in api_do_preprocess
heygem-tts | tts_item: TtsItem = build_tts_item(req)
heygem-tts | File "/code/tools/server/views_guiji.py", line 54, in build_tts_item
heygem-tts | raise Exception('file not exists')
heygem-tts | Exception: file not exists
heygem-tts |
heygem-tts | 2025-05-05 05:57:08.952 | INFO | tools.server.views_guiji:api_do_preprocess:170 - 训练返回结果：{'code': -1, 'msg': 'file not exists'}
heygem-tts | INFO: 172.21.0.1:41084 - "POST /v1/preprocess_and_tran HTTP/1.1" 200 OK
heygem-tts | 2025-05-05 05:57:57.743 | INFO | tools.server.views_guiji:api_do_preprocess:144 - 收到训练请求：reference_audio='origin_audio/20250505135757583.wav' format='wav' lang='zh'
heygem-tts | 2025-05-05 05:57:57.743 | INFO | tools.server.views_guiji:build_tts_item:47 - 创建会话目录：/code/sessions/20250505/4edd45889c9543048a84a741d77db49b
heygem-tts | 2025-05-05 05:57:57.744 | INFO | tools.server.views_guiji:build_tts_item:52 - reference_audio不是url地址，本地路径为：/code/data/origin_audio/20250505135757583.wav
heygem-tts | 2025-05-05 05:57:57.744 | ERROR | tools.server.views_guiji:api_do_preprocess:167 - An error occurred: file not exists
heygem-tts | Stack trace:
heygem-tts | Traceback (most recent call last):
heygem-tts | File "/code/tools/server/views_guiji.py", line 151, in api_do_preprocess
heygem-tts | tts_item: TtsItem = build_tts_item(req)
heygem-tts | File "/code/tools/server/views_guiji.py", line 54, in build_tts_item
heygem-tts | raise Exception('file not exists')
heygem-tts | Exception: file not exists
heygem-tts |
heygem-tts | 2025-05-05 05:57:57.744 | INFO | tools.server.views_guiji:api_do_preprocess:170 - 训练返回结果：{'code': -1, 'msg': 'file not exists'}
heygem-tts | INFO: 172.21.0.1:60368 - "POST /v1/preprocess_and_tran HTTP/1.1" 200 OK
heygem-tts | 2025-05-05 05:58:23.304 | INFO | tools.server.views_guiji:api_do_preprocess:144 - 收到训练请求：reference_audio='origin_audio/20250505135823126.wav' format='wav' lang='zh'
heygem-tts | 2025-05-05 05:58:23.304 | INFO | tools.server.views_guiji:build_tts_item:47 - 创建会话目录：/code/sessions/20250505/87aabfee2cf94dfbb689c51960866794
heygem-tts | 2025-05-05 05:58:23.305 | INFO | tools.server.views_guiji:build_tts_item:52 - reference_audio不是url地址，本地路径为：/code/data/origin_audio/20250505135823126.wav
heygem-tts | 2025-05-05 05:58:23.306 | ERROR | tools.server.views_guiji:api_do_preprocess:167 - An error occurred: file not exists
heygem-tts | Stack trace:
heygem-tts | Traceback (most recent call last):
heygem-tts | File "/code/tools/server/views_guiji.py", line 151, in api_do_preprocess
heygem-tts | tts_item: TtsItem = build_tts_item(req)
heygem-tts | File "/code/tools/server/views_guiji.py", line 54, in build_tts_item
heygem-tts | raise Exception('file not exists')
heygem-tts | Exception: file not exists
heygem-tts |
heygem-tts | 2025-05-05 05:58:23.306 | INFO | tools.server.views_guiji:api_do_preprocess:170 - 训练返回结果：{'code': -1, 'msg': 'file not exists'}
heygem-tts | INFO: 172.21.0.1:39638 - "POST /v1/preprocess_and_tran HTTP/1.1" 200 OK
heygem-gen-video | [2025-05-05 05:59:10] [_internal.py[line:97]] [INFO] [172.21.0.1 - - [05/May/2025 05:59:10] "GET / HTTP/1.1" 404 -]
heygem-gen-video | [2025-05-05 05:59:10] [_internal.py[line:97]] [INFO] [172.21.0.1 - - [05/May/2025 05:59:10] "GET / HTTP/1.1" 404 -]
heygem-gen-video | [2025-05-05 05:59:10] [_internal.py[line:97]] [INFO] [172.21.0.1 - - [05/May/2025 05:59:10] "GET / HTTP/1.1" 404 -]
As stated in the link below, you need at least 32GB VRam to run it.
https://mp.weixin.qq.com/s/vKiBR85E7JyRkr6CxLCppA?mpshare=1&scene=1&srcid=0319sszkopZO6870sGsU0TFc&sharer_shareinfo=cac5ec3bfa62ed558552c7c022821613&sharer_shareinfo_first=cac5ec3bfa62ed558552c7c022821613&from=industrynews#rd
As stated in the link below, you need at least 32GB VRam to run it.
https://mp.weixin.qq.com/s/vKiBR85E7JyRkr6CxLCppA?mpshare=1&scene=1&srcid=0319sszkopZO6870sGsU0TFc&sharer_shareinfo=cac5ec3bfa62ed558552c7c022821613&sharer_shareinfo_first=cac5ec3bfa62ed558552c7c022821613&from=industrynews#rd
根本就不是这个问题，我已经找到原因了，映射的目录必须是默认的，改了不可以，项目的前端被写死路径了，我用回默认的映射路径才可以
As stated in the link below, you need at least 32GB VRam to run it. https://mp.weixin.qq.com/s/vKiBR85E7JyRkr6CxLCppA?mpshare=1&scene=1&srcid=0319sszkopZO6870sGsU0TFc&sharer_shareinfo=cac5ec3bfa62ed558552c7c022821613&sharer_shareinfo_first=cac5ec3bfa62ed558552c7c022821613&from=industrynews#rd
根本就不是这个问题，我已经找到原因了，映射的目录必须是默认的，改了不可以，项目的前端被写死路径了，我用回默认的映射路径才可以
测试了，也还是不行，即便我使用了默认的d:/heygem_data/.. 也依然会有这个报错。感觉上是tts那边没有收到/存储下来？
查看了所有的issue，我这里已经解决了，总结下来： 1、视频文件可能没有音频 2、系统内存小（<16GB)，32GB 可以OK，如果不行需要修改 %USERPROFILE%/.wslconfig，具体看官方常见问题 ：
[wsl2]
memory=15GB
3、DOCKER需要开启 “Enable host networking” ，在 resources/network下。 4、确认所有系统启动完成，启动成功后需要等待一会。
查看了所有的issue，我这里已经解决了，总结下来： 1、视频文件可能没有音频 2、系统内存小（<16GB)，32GB 可以OK，如果不行需要修改 %USERPROFILE%/.wslconfig，具体看官方常见问题 ：
[wsl2] memory=15GB3、DOCKER 得把“启用主机网络”给打开，就在 resources/network 下面。 4、确认所有系统启动完成，启动成功后需要等待一会。
再加一条 volumes: - d:/heygem_data/voice/data:/code/data volumes: - d:/heygem_data/face2face:/code/data 这两个配置别改,估计是写死了.
查看了所有的issue，我这里已经解决了，总结下来： 1、视频文件可能没有音频 2、系统内存小（<16GB)，32GB 可以OK，如果不行需要修改 %USERPROFILE%/.wslconfig，具体看官方常见问题 ：
[wsl2] memory=15GB3、DOCKER需要开启 “Enable host networking” ，在 resources/network下。 4、确认所有系统启动完成，启动成功后需要等待一会。
我电脑16GB内存，在wslconfig文件内加memory=15GB后就没报错。
查看了所有的issue，我这里已经解决了，总结下来： 1、视频文件可能没有音频 2、系统内存小（<16GB)，32GB 可以OK，如果不行需要修改 %USERPROFILE%/.wslconfig，具体看官方常见问题 ：
[wsl2] memory=15GB3、DOCKER需要开启 “Enable host networking” ，在 resources/network下。 4、确认所有系统启动完成，启动成功后需要等待一会。
我电脑16GB内存，在wslconfig文件内加memory=15GB后就没报错。
谢谢，这个方法可行。目前猜测可能是因为wsl默认只使用物理机一半的内存，即8GB。现在手动设置为15GB就正常了
由于版本还不完善，Duix.Avatar的客户端有好多硬编码，针对Windows系统，docker-compose.yaml文件必须用到D:\duix_avatar_data。 客户端同样也写死了用D:\duix_avatar_data，其实，docker-compose.yaml中用到了两个文件夹 face2face和voice。 对于Linux客户端，这个duix_avatar_data目录是在用户的主目录下，所以docker-compose.yaml中必须把挂载卷的路径写成： volumes: - /home/ronsun/duix_avatar_data/voice/data:/code/data
volumes: - /home/ronsun/duix_avatar_data/face2face:/code/data
