search

anhnh2002 / XTTSv2-Finetuning-for-New-Languages

60 stars 17 forks source link

AssertionError #24

Closed readysj closed 4 days ago

readysj commented 5 days ago

I have trin tamil text to speech with my own voice. everything working fine. But when i try train this error message received" 24s

2024-10-26 11:14:16.494389: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:485] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2024-10-26 11:14:16.514481: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:8454] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2024-10-26 11:14:16.520378: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1452] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2024-10-26 11:14:16.535999: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2024-10-26 11:14:17.640517: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT /content/drive/MyDrive/Tamil_TTS_Data/metadata_train_v2.csv /content/drive/MyDrive/Tamil_TTS_Data/metadata_eval_v2.csv ta /content/XTTSv2-Finetuning-for-New-Languages/TTS/utils/io.py:54: 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. return torch.load(f, map_location=map_location, **kwargs) /content/XTTSv2-Finetuning-for-New-Languages/TTS/tts/layers/tortoise/arch_utils.py:336: 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. self.mel_norms = torch.load(f) /content/XTTSv2-Finetuning-for-New-Languages/TTS/tts/layers/xtts/trainer/gpt_trainer.py:186: 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. dvae_checkpoint = torch.load(self.args.dvae_checkpoint, map_location=torch.device("cpu"))

DVAE weights restored from: checkpoints/XTTS_v2.0_original_model_files/dvae.pth Traceback (most recent call last): File "/content/XTTSv2-Finetuning-for-New-Languages/train_gpt_xtts.py", line 224, in trainer_out_path = train_gpt( File "/content/XTTSv2-Finetuning-for-New-Languages/train_gpt_xtts.py", line 184, in train_gpt train_samples, eval_samples = load_tts_samples( File "/content/XTTSv2-Finetuning-for-New-Languages/TTS/tts/datasets/init.py", line 120, in load_tts_samples meta_data_train = formatter(root_path, meta_file_train, ignored_speakers=ignored_speakers) File "/content/XTTSv2-Finetuning-for-New-Languages/TTS/tts/datasets/formatters.py", line 67, in coqui assert all(x in metadata.columns for x in ["audio_file", "text"]) AssertionError" Please help how to fix this or please provide step-by-step for train tamil text to speech with my own voice"

anhnh2002 commented 4 days ago

You must format metadata files as indicated in the README

Screenshot 2024-10-27 at 19 39 25