讨论 问题反馈 声音克隆总是失败

声音克隆总是失败

qiniugankao 发表于    阅读:21    回复:0

声音克隆总是失败,报一个

Error: Error invoking remote method 'server:callFunction': [object Object]

另外启动cosyvoice模型日志如下:

[PYI-19508:DEBUG] PyInstaller Bootloader 6.x

1

[PYI-19508:DEBUG] LOADER: executable file: D:\mode\server-cosyvoice-win-x86-v0.0.4\main.exe

2

[PYI-19508:DEBUG] LOADER: trying to load executable-embedded archive...

3

[PYI-19508:DEBUG] LOADER: attempting to open archive D:\mode\server-cosyvoice-win-x86-v0.0.4\main.exe

4

[PYI-19508:DEBUG] LOADER: cookie found at offset 0x30F42AF

5

[PYI-19508:DEBUG] LOADER: archive file: D:\mode\server-cosyvoice-win-x86-v0.0.4\main.exe

6

[PYI-19508:DEBUG] LOADER: application has onedir semantics...

7

[PYI-19508:DEBUG] LOADER: _PYI_ARCHIVE_FILE not defined...

8

[PYI-19508:DEBUG] LOADER: process level = 1

9

[PYI-19508:DEBUG] LOADER: application's top-level directory: D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep

10

[PYI-19508:DEBUG] LOADER: calling SetDllDirectory: D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep

11

[PYI-19508:DEBUG] LOADER: splash screen is unavailable.

12

[PYI-19508:DEBUG] LOADER: ucrtbase.dll found: D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\ucrtbase.dll

13

[PYI-19508:DEBUG] LOADER: loading Python shared library: D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\python38.dll

14

[PYI-19508:DEBUG] LOADER: loaded functions from Python shared library.

15

[PYI-19508:DEBUG] LOADER: pre-initializing embedded python interpreter...

16

[PYI-19508:DEBUG] LOADER: creating PyConfig structure...

17

[PYI-19508:DEBUG] LOADER: initializing interpreter configuration...

18

[PYI-19508:DEBUG] LOADER: setting program name...

19

[PYI-19508:DEBUG] LOADER: setting python home path...

20

[PYI-19508:DEBUG] LOADER: setting module search paths...

21

[PYI-19508:DEBUG] LOADER: setting sys.argv...

22

[PYI-19508:DEBUG] LOADER: applying run-time options...

23

[PYI-19508:DEBUG] LOADER: starting embedded python interpreter...

24

[PYI-19508:DEBUG] LOADER: setting sys._MEIPASS

25

[PYI-19508:DEBUG] LOADER: importing modules from PKG/CArchive

26

[PYI-19508:DEBUG] LOADER: extracted struct

27

[PYI-19508:DEBUG] LOADER: running unmarshalled code object for module struct...

28

[PYI-19508:DEBUG] LOADER: extracted pyimod01_archive

29

[PYI-19508:DEBUG] LOADER: running unmarshalled code object for module pyimod01_archive...

30

[PYI-19508:DEBUG] LOADER: extracted pyimod02_importers

31

[PYI-19508:DEBUG] LOADER: running unmarshalled code object for module pyimod02_importers...

32

[PYI-19508:DEBUG] LOADER: extracted pyimod03_ctypes

33

[PYI-19508:DEBUG] LOADER: running unmarshalled code object for module pyimod03_ctypes...

34

[PYI-19508:DEBUG] LOADER: extracted pyimod04_pywin32

35

[PYI-19508:DEBUG] LOADER: running unmarshalled code object for module pyimod04_pywin32...

36

[PYI-19508:DEBUG] LOADER: looking for PYZ archive TOC entry...

37

[PYI-19508:DEBUG] LOADER: path to PYZ archive stored into sys._pyinstaller_pyz...

38

[PYI-19508:DEBUG] LOADER: running pyiboot01_bootstrap.py

39

[PYI-19508:DEBUG] LOADER: running pyi_rth_inspect.py

40

[PYI-19508:DEBUG] LOADER: running pyi_rth_pkgutil.py

41

[PYI-19508:DEBUG] LOADER: running pyi_rth_multiprocessing.py

42

[PYI-19508:DEBUG] LOADER: running pyi_rth_setuptools.py

43

[PYI-19508:DEBUG] LOADER: running pyi_rth_pkgres.py

44

[PYI-19508:DEBUG] LOADER: running pyi_rth_cryptography_openssl.py

45

[PYI-19508:DEBUG] LOADER: running pyi_rth_mplconfig.py

46

[PYI-19508:DEBUG] LOADER: running pyi_rth__tkinter.py

47

[PYI-19508:DEBUG] LOADER: running webui.py

48

2025-02-04 14:49:14,699 - modelscope - INFO - PyTorch version 2.4.1+cu118 Found.

49

2025-02-04 14:49:14,703 - modelscope - INFO - Loading ast index from C:\Users\mengmeng\.cache\modelscope\ast_indexer

50

2025-02-04 14:49:14,707 - modelscope - INFO - Loading done! Current index file version is 1.15.0, with md5 d41d8cd98f00b204e9800998ecf8427e and a total number of 0 components indexed

51

2025-02-04 14:49:19,292 DEBUG Attempting to acquire lock 2376475885088 on D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\static_ffmpeg\lock.file

52

2025-02-04 14:49:19,293 DEBUG Lock 2376475885088 acquired on D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\static_ffmpeg\lock.file

53

2025-02-04 14:49:19,294 DEBUG Attempting to release lock 2376475885088 on D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\static_ffmpeg\lock.file

54

2025-02-04 14:49:19,295 DEBUG Lock 2376475885088 released on D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\static_ffmpeg\lock.file

55

D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\diffusers\models\lora.py:393: FutureWarning: `LoRACompatibleLinear` is deprecated and will be removed in version 1.0.0. Use of `LoRACompatibleLinear` is deprecated. Please switch to PEFT backend by installing PEFT: `pip install peft`.

56

deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message)

57

2025-02-04 14:49:28,502 INFO input frame rate=50

58

torch\nn\utils\weight_norm.py:134: FutureWarning: `torch.nn.utils.weight_norm` is deprecated in favor of `torch.nn.utils.parametrizations.weight_norm`.

59

WeightNorm.apply(module, name, dim)

60

D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\cosyvoice\dataset\processor.py:24: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. With dispatcher enabled, this function is no-op. You can remove the function call.

61

torchaudio.set_audio_backend('soundfile')

62

onnxruntime\capi\onnxruntime_inference_collection.py:69: UserWarning: Specified provider 'CUDAExecutionProvider' is not in available provider names.Available providers: 'AzureExecutionProvider, CPUExecutionProvider'

63

warnings.warn(

64

D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\cosyvoice\cli\frontend.py:57: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.

65

self.spk2info = torch.load(spk2info, map_location=self.device)

66

2025-02-04 14:49:31,607 WETEXT INFO found existing fst: D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\tn\zh_tn_tagger.fst

67

2025-02-04 14:49:31,607 INFO found existing fst: D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\tn\zh_tn_tagger.fst

68

2025-02-04 14:49:31,608 WETEXT INFO D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\tn\zh_tn_verbalizer.fst

69

2025-02-04 14:49:31,608 INFO D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\tn\zh_tn_verbalizer.fst

70

2025-02-04 14:49:31,608 WETEXT INFO skip building fst for zh_normalizer ...

71

2025-02-04 14:49:31,608 INFO skip building fst for zh_normalizer ...

72

2025-02-04 14:49:32,470 WETEXT INFO found existing fst: D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\tn\en_tn_tagger.fst

73

2025-02-04 14:49:32,470 INFO found existing fst: D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\tn\en_tn_tagger.fst

74

2025-02-04 14:49:32,470 WETEXT INFO D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\tn\en_tn_verbalizer.fst

75

2025-02-04 14:49:32,470 INFO D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\tn\en_tn_verbalizer.fst

76

2025-02-04 14:49:32,470 WETEXT INFO skip building fst for en_normalizer ...

77

2025-02-04 14:49:32,470 INFO skip building fst for en_normalizer ...

78

D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\cosyvoice\cli\model.py:57: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.

79

self.llm.load_state_dict(torch.load(llm_model, map_location=self.device))

80

D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\cosyvoice\cli\model.py:60: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.

81

self.flow.load_state_dict(torch.load(flow_model, map_location=self.device))

82

D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\cosyvoice\cli\model.py:62: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.

83

self.hift.load_state_dict(torch.load(hift_model, map_location=self.device))

84

2025-02-04 14:49:41,022 DEBUG load_ssl_context verify=True cert=None trust_env=True http2=False

85

2025-02-04 14:49:41,023 DEBUG load_verify_locations cafile='D:\\mode\\server-cosyvoice-win-x86-v0.0.4\\_dep\\certifi\\cacert.pem'

86

2025-02-04 14:49:41,026 DEBUG Using proactor: IocpProactor

87

2025-02-04 14:49:41,039 DEBUG load_ssl_context verify=True cert=None trust_env=True http2=False

88

2025-02-04 14:49:41,068 DEBUG load_verify_locations cafile='D:\\mode\\server-cosyvoice-win-x86-v0.0.4\\_dep\\certifi\\cacert.pem'

89

D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\gradio\components\base.py:190: UserWarning: 'scale' value should be an integer. Using 0.5 will cause issues.

90

warnings.warn(

91

D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\gradio\components\base.py:190: UserWarning: 'scale' value should be an integer. Using 0.25 will cause issues.

92

warnings.warn(

93

D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep\gradio\layouts\column.py:55: UserWarning: 'scale' value should be an integer. Using 0.25 will cause issues.

94

warnings.warn(

95

2025-02-04 14:49:41,266 DEBUG Using proactor: IocpProactor

96

INFO: Started server process [19508]

97

INFO: Waiting for application startup.

98

INFO: Application startup complete.

99

INFO: Uvicorn running on http://127.0.0.1:50617 (Press CTRL+C to quit)

100

2025-02-04 14:49:42,002 DEBUG load_ssl_context verify=True cert=None trust_env=True http2=False

101

2025-02-04 14:49:42,002 DEBUG load_verify_locations cafile='D:\\mode\\server-cosyvoice-win-x86-v0.0.4\\_dep\\certifi\\cacert.pem'

102

2025-02-04 14:49:42,060 DEBUG load_ssl_context verify=True cert=None trust_env=True http2=False

103

2025-02-04 14:49:42,061 DEBUG load_verify_locations cafile='D:\\mode\\server-cosyvoice-win-x86-v0.0.4\\_dep\\certifi\\cacert.pem'

104

2025-02-04 14:49:43,087 DEBUG load_ssl_context verify=True cert=None trust_env=True http2=False

105

2025-02-04 14:49:43,088 DEBUG load_verify_locations cafile='D:\\mode\\server-cosyvoice-win-x86-v0.0.4\\_dep\\certifi\\cacert.pem'

106

2025-02-04 14:49:43,206 DEBUG load_ssl_context verify=True cert=None trust_env=True http2=False

107

2025-02-04 14:49:43,206 DEBUG load_verify_locations cafile='D:\\mode\\server-cosyvoice-win-x86-v0.0.4\\_dep\\certifi\\cacert.pem'

108

2025-02-04 14:49:44,062 DEBUG connect_tcp.started host='127.0.0.1' port=7890 local_address=None timeout=3 socket_options=None

109

2025-02-04 14:49:44,063 DEBUG connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x000002295C915550>

110

2025-02-04 14:49:44,189 DEBUG connect_tcp.started host='127.0.0.1' port=7890 local_address=None timeout=3 socket_options=None

111

2025-02-04 14:49:44,190 DEBUG connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x000002295C9159D0>

112

2025-02-04 14:49:45,140 DEBUG start_tls.started ssl_context=<ssl.SSLContext object at 0x000002295C920740> server_hostname='127.0.0.1' timeout=3

113

2025-02-04 14:49:45,141 DEBUG start_tls.failed exception=ConnectError(SSLZeroReturnError(6, 'TLS/SSL connection has been closed (EOF) (_ssl.c:1149)'))

114

2025-02-04 14:49:45,273 DEBUG start_tls.started ssl_context=<ssl.SSLContext object at 0x000002295C9206C0> server_hostname='127.0.0.1' timeout=3

115

2025-02-04 14:49:45,274 DEBUG start_tls.failed exception=ConnectError(SSLZeroReturnError(6, 'TLS/SSL connection has been closed (EOF) (_ssl.c:1149)'))

116

2025-02-04 14:49:45,285 DEBUG Starting new HTTPS connection (1): huggingface.co:443

117

transformer is not installed, please install it if you want to use related modules

118

failed to import ttsfrd, use WeTextProcessing instead

119

##################### MSBrick Info #####################

120

root: D:\mode\server-cosyvoice-win-x86-v0.0.4\_dep

121

args: Namespace(gpu_mode='', model_dir='D:\\mode\\server-cosyvoice-win-x86-v0.0.4\\_dep\\pretrained_models/CosyVoice-300M', port=50617)

122

######################################################

123

INFO: 127.0.0.1:4036 - "GET /config HTTP/1.1" 200 OK

124

INFO: 127.0.0.1:4040 - "GET /info HTTP/1.1" 200 OK

125

INFO: 127.0.0.1:4036 - "POST /queue/join HTTP/1.1" 200 OK

126

INFO: 127.0.0.1:4040 - "GET /queue/data?session_hash=y35i8mf9ce HTTP/1.1" 200 OK


里面有一些failed 和ERR提示 是缺少某些模型吗?

我来评论
语言
QQ
微信客服
微信群
客服