(robot_clone) E:\yanjiuyuan\robot\Cosyvoice>python main_test.py
2024-09-30 10:33:51,776 - modelscope - INFO - PyTorch version 2.0.1+cu118 Found.
2024-09-30 10:33:51,778 - modelscope - INFO - Loading ast index from C:\Users\Administrator.cache\modelscope\ast_indexer
2024-09-30 10:33:51,889 - modelscope - INFO - Loading done! Current index file version is 1.15.0, with md5 16066b37e1484529497a75230652add4 and a total number of 980 components indexed
failed to import ttsfrd, use WeTextProcessing instead
D:\software_download\anaconda\envs\robot_clone\lib\site-packages\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.
deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message)
2024-09-30 10:33:56,454 INFO input frame rate=25
Traceback (most recent call last):
File "E:\yanjiuyuan\robot\Cosyvoice\main_test.py", line 12, in
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-25Hz') # or change to pretrained_models/CosyVoice-300M for 50Hz inference
File "E:\yanjiuyuan\robot\Cosyvoice\cosyvoice\cli\cosyvoice.py", line 32, in init
configs = load_hyperpyyaml(f)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\hyperpyyaml\core.py", line 188, in load_hyperpyyaml
hparams = yaml.load(yaml_stream, Loader=loader)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\yaml__init__.py", line 81, in load
return loader.get_single_data()
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 116, in get_single_data
return self.construct_document(node)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 120, in construct_document
data = self.construct_object(node)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 147, in construct_object
data = self.construct_non_recursive_object(node)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 188, in construct_non_recursive_object
for _dummy in generator:
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 633, in construct_yaml_map
value = self.construct_mapping(node)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 429, in construct_mapping
return BaseConstructor.construct_mapping(self, node, deep=deep)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 244, in construct_mapping
value = self.construct_object(value_node, deep=deep)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 147, in construct_object
data = self.construct_non_recursive_object(node)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 183, in construct_non_recursive_object
data = constructor(self, tag_suffix, node)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\hyperpyyaml\core.py", line 491, in _construct_name
raise ImportError("There is no such entity as %s" % callable_string)
ImportError: There is no such entity as cosyvoice.tokenizer.tokenizer.get_tokenizer
相关代码如下：
from cosyvoice.cli.cosyvoice import CosyVoice
from cosyvoice.utils.file_utils import load_wav
import torchaudio
import os, sys
sys.path.insert(0, os.path.abspath('third_party/Matcha-TTS'))
import time
start_time = time.time()
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-25Hz') # or change to pretrained_models/CosyVoice-300M for 50Hz inference
zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean
prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
for i, j in enumerate(cosyvoice.inference_zero_shot('收到好友从远方寄来的生日礼物，那份意外的惊喜与深深的祝福让我心中充满了甜蜜的快乐，笑容如花儿般绽放。', '希望你以后能够做的比我还好呦。', prompt_speech_16k, stream=False)):
torchaudio.save('zeroshot{}.wav'.format(i), j['tts_speech'], 22050)
HUIZI66889
commented
2 months ago
报错信息如下：
(robot_clone) E:\yanjiuyuan\robot\Cosyvoice>python main_test.py 2024-09-30 10:33:51,776 - modelscope - INFO - PyTorch version 2.0.1+cu118 Found. 2024-09-30 10:33:51,778 - modelscope - INFO - Loading ast index from C:\Users\Administrator.cache\modelscope\ast_indexer 2024-09-30 10:33:51,889 - modelscope - INFO - Loading done! Current index file version is 1.15.0, with md5 16066b37e1484529497a75230652add4 and a total number of 980 components indexed failed to import ttsfrd, use WeTextProcessing instead D:\software_download\anaconda\envs\robot_clone\lib\site-packages\diffusers\models\lora.py:393: FutureWarning:
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-25Hz') # or change to pretrained_models/CosyVoice-300M for 50Hz inference
File "E:\yanjiuyuan\robot\Cosyvoice\cosyvoice\cli\cosyvoice.py", line 32, in init
configs = load_hyperpyyaml(f)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\hyperpyyaml\core.py", line 188, in load_hyperpyyaml
hparams = yaml.load(yaml_stream, Loader=loader)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\yaml__init__.py", line 81, in load
return loader.get_single_data()
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 116, in get_single_data
return self.construct_document(node)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 120, in construct_document
data = self.construct_object(node)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 147, in construct_object
data = self.construct_non_recursive_object(node)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 188, in construct_non_recursive_object
for _dummy in generator:
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 633, in construct_yaml_map
value = self.construct_mapping(node)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 429, in construct_mapping
return BaseConstructor.construct_mapping(self, node, deep=deep)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 244, in construct_mapping
value = self.construct_object(value_node, deep=deep)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 147, in construct_object
data = self.construct_non_recursive_object(node)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\ruamel\yaml\constructor.py", line 183, in construct_non_recursive_object
data = constructor(self, tag_suffix, node)
File "D:\software_download\anaconda\envs\robot_clone\lib\site-packages\hyperpyyaml\core.py", line 491, in _construct_name
raise ImportError("There is no such entity as %s" % callable_string)
ImportError: There is no such entity as cosyvoice.tokenizer.tokenizer.get_tokenizer
LoRACompatibleLinearis deprecated and will be removed in version 1.0.0. Use ofLoRACompatibleLinearis deprecated. Please switch to PEFT backend by installing PEFT:pip install peft. deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message) 2024-09-30 10:33:56,454 INFO input frame rate=25 Traceback (most recent call last): File "E:\yanjiuyuan\robot\Cosyvoice\main_test.py", line 12, in相关代码如下：
from cosyvoice.cli.cosyvoice import CosyVoice from cosyvoice.utils.file_utils import load_wav import torchaudio import os, sys sys.path.insert(0, os.path.abspath('third_party/Matcha-TTS')) import time
start_time = time.time() cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-25Hz') # or change to pretrained_models/CosyVoice-300M for 50Hz inference
zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean
prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000) for i, j in enumerate(cosyvoice.inference_zero_shot('收到好友从远方寄来的生日礼物，那份意外的惊喜与深深的祝福让我心中充满了甜蜜的快乐，笑容如花儿般绽放。', '希望你以后能够做的比我还好呦。', prompt_speech_16k, stream=False)): torchaudio.save('zeroshot{}.wav'.format(i), j['tts_speech'], 22050)
print("总共用时：", time.time()-start_time)
请问该报错要如何解决呢？