NO module name Architectures. I am trying to train on a new language.

[donwany]

command: python /home/ts75080/Documents/IMS-Toucan/TrainingPipelines/finetuning_example_simple_ewe.py finetuning_example_simple_ewe \ --gpu_id 0 \ --finetune \ --resume

Traceback (most recent call last): File "/home/ts75080/Documents/IMS-Toucan/TrainingPipelines/finetuning_example_simple_ewe.py", line 12, in from Architectures.ToucanTTS.ToucanTTS import ToucanTTS ModuleNotFoundError: No module named 'Architectures'

[Flux9665]

The problem is that you execute a script in the TrainingPipelines directory. Instead you need to run the run_training_pipeline.py script on the top level. In the TrainingPipelines directory you just define the data and model configuration, but then you import the pipeline you have built in the run_training_pipeline script and execute it from there. Python sees all paths relative to the location of the script you execute.

[donwany]

corrected it. but getting this errors again. Anyhelp? Am using ubuntu 22.04

Making GPU 0 the only visible device(s). Preparing ... building dataset cache ... /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. downloading model 042801_base from: https://github.com/xinjli/transphone/releases/download/v1.0/042801_base.tar.gz to: /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/transphone/data/model please wait... Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. downloading model 042801_base from: https://github.com/xinjli/transphone/releases/download/v1.0/042801_base.tar.gz to: /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/transphone/data/model please wait... downloading model 042801_base from: https://github.com/xinjli/transphone/releases/download/v1.0/042801_base.tar.gz to: /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/transphone/data/model please wait... Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. downloading model 042801_base from: https://github.com/xinjli/transphone/releases/download/v1.0/042801_base.tar.gz to: /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/transphone/data/model please wait... /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. downloading model 042801_base from: https://github.com/xinjli/transphone/releases/download/v1.0/042801_base.tar.gz to: /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/transphone/data/model please wait... Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. downloading model 042801_base from: https://github.com/xinjli/transphone/releases/download/v1.0/042801_base.tar.gz to: /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/transphone/data/model please wait... Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. downloading model 042801_base from: https://github.com/xinjli/transphone/releases/download/v1.0/042801_base.tar.gz to: /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/transphone/data/model please wait... Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. downloading model 042801_base from: https://github.com/xinjli/transphone/releases/download/v1.0/042801_base.tar.gz to: /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/transphone/data/model please wait... Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. downloading model 042801_base from: https://github.com/xinjli/transphone/releases/download/v1.0/042801_base.tar.gz to: /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/transphone/data/model please wait... Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. downloading model 042801_base from: https://github.com/xinjli/transphone/releases/download/v1.0/042801_base.tar.gz to: /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/transphone/data/model please wait... /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") Process Process-7: Traceback (most recent call last): File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 108, in run self._target(*self._args, self._kwargs) File "/home/ts75080/Documents/IMS-Toucan/Architectures/Aligner/CodecAlignerDataset.py", line 238, in _cache_builderprocess , sr = sf.read(path_list[0]) IndexError: list index out of range /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") Process Process-8: Traceback (most recent call last): File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 108, in run self._target(*self._args, *self._kwargs) File "/home/ts75080/Documents/IMS-Toucan/Architectures/Aligner/CodecAlignerDataset.py", line 238, in _cache_builderprocess , sr = sf.read(path_list[0]) IndexError: list index out of range /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") Process Process-11: Traceback (most recent call last): File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 108, in run self._target(self._args, self._kwargs) File "/home/ts75080/Documents/IMS-Toucan/Architectures/Aligner/CodecAlignerDataset.py", line 238, in _cache_builderprocess , sr = sf.read(path_list[0]) IndexError: list index out of range /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") Process Process-10: Traceback (most recent call last): File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 108, in run self._target(*self._args, *self._kwargs) File "/home/ts75080/Documents/IMS-Toucan/Architectures/Aligner/CodecAlignerDataset.py", line 238, in _cache_builderprocess , sr = sf.read(path_list[0]) IndexError: list index out of range /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") Process Process-2: Traceback (most recent call last): File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 108, in run self._target(self._args, **self._kwargs) File "/home/ts75080/Documents/IMS-Toucan/Architectures/Aligner/CodecAlignerDataset.py", line 238, in _cache_builderprocess , sr = sf.read(path_list[0]) IndexError: list index out of range /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") Process Process-3: Traceback (most recent call last): File "/home/ts75080/Documents/IMS-Toucan/Preprocessing/TextFrontend.py", line 562, in init self.phonemizer_backend = EspeakBackend( File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/phonemizer/backend/espeak/espeak.py", line 45, in init super().init( File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/phonemizer/backend/espeak/base.py", line 39, in init super().init( File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/phonemizer/backend/base.py", line 86, in init self._language = self._init_language(language) File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/phonemizer/backend/base.py", line 100, in _init_language raise RuntimeError( RuntimeError: language "ee" is not supported by the espeak backend

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 108, in run self._target(*self._args, self._kwargs) File "/home/ts75080/Documents/IMS-Toucan/Architectures/Aligner/CodecAlignerDataset.py", line 237, in _cache_builder_process tf = ArticulatoryCombinedTextFrontend(language=lang) File "/home/ts75080/Documents/IMS-Toucan/Preprocessing/TextFrontend.py", line 580, in init self.transphone = read_g2p() File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/transphone/g2p.py", line 61, in read_g2p model = G2P(checkpoint, cache_path, config) File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/transphone/utils.py", line 17, in call cls._instances[cls] = super(Singleton, cls).call(*args, *kwargs) File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/transphone/g2p.py", line 111, in init torch_load(self.model, self.checkpoint) File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/transphone/model/checkpoint_utils.py", line 62, in torch_load model_state_dict = torch.load(str(path), map_location=torch.device('cpu')) File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/serialization.py", line 1004, in load with _open_zipfile_reader(opened_file) as opened_zipfile: File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/serialization.py", line 456, in init super().init(torch._C.PyTorchFileReader(name_or_buffer)) RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") Process Process-4: Traceback (most recent call last): File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 108, in run self._target(self._args, self._kwargs) File "/home/ts75080/Documents/IMS-Toucan/Architectures/Aligner/CodecAlignerDataset.py", line 238, in _cache_builderprocess , sr = sf.read(path_list[0]) IndexError: list index out of range /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") Process Process-5: Traceback (most recent call last): File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 108, in run self._target(*self._args, self._kwargs) File "/home/ts75080/Documents/IMS-Toucan/Architectures/Aligner/CodecAlignerDataset.py", line 238, in _cache_builderprocess , sr = sf.read(path_list[0]) IndexError: list index out of range /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") Process Process-6: Traceback (most recent call last): File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 108, in run self._target(*self._args, *self._kwargs) File "/home/ts75080/Documents/IMS-Toucan/Architectures/Aligner/CodecAlignerDataset.py", line 238, in _cache_builderprocess , sr = sf.read(path_list[0]) IndexError: list index out of range /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") Process Process-9: Traceback (most recent call last): File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/multiprocessing/process.py", line 108, in run self._target(self._args, self._kwargs) File "/home/ts75080/Documents/IMS-Toucan/Architectures/Aligner/CodecAlignerDataset.py", line 238, in _cache_builderprocess , sr = sf.read(path_list[0]) IndexError: list index out of range pooling results... converting text to tensors... converting speech to tensors... converting waves to tensors... unpacking file list... done! 0it [00:00, ?it/s] Traceback (most recent call last): File "/home/ts75080/Documents/IMS-Toucan/run_training_pipeline.py", line 143, in pipeline_dict[args.pipeline]( File "/home/ts75080/Documents/IMS-Toucan/TrainingPipelines/finetuning_example_simple_ewe.py", line 48, in run train_data = prepare_tts_corpus( File "/home/ts75080/Documents/IMS-Toucan/Utility/corpus_preparation.py", line 52, in prepare_tts_corpus prepare_aligner_corpus( File "/home/ts75080/Documents/IMS-Toucan/Utility/corpus_preparation.py", line 13, in prepare_aligner_corpus return CodecAlignerDataset( File "/home/ts75080/Documents/IMS-Toucan/Architectures/Aligner/CodecAlignerDataset.py", line 43, in init self._build_dataset_cache( File "/home/ts75080/Documents/IMS-Toucan/Architectures/Aligner/CodecAlignerDataset.py", line 199, in _build_dataset_cache raise RuntimeError # something went wrong and there are no datapoints RuntimeError

[Flux9665]

It seems your path_to_transcript_dict is either empty or incorrect.

[donwany]

It seems your path_to_transcript_dict is either empty or incorrect.

I think the training pipeline does not support low resource languages like Ewe

[donwany]

It seems your path_to_transcript_dict is either empty or incorrect.

Can you check my repo and see what am doing wrong?

https://github.com/donwany/IMS-Tousan-Ewe.git

finetuning script is here: https://github.com/donwany/IMS-Tousan-Ewe/blob/main/fine_tune_model.sh

[Flux9665]

Ewe is supported, you are using the correct language code in your train pipeline as well. I don't see an obvious mistake anywhere, everything seems fine. When you execute the script, is it still the same errors as you posted above?

This part of the error message tells me that the dictionary that holds the mapping from filepaths to transcripts seems to be empty:

_, sr = sf.read(path_list[0])
IndexError: list index out of range

What is shown when you print the result of build_path_to_transcript_dict_ewe()?

[donwany]

Ewe is supported, you are using the correct language code in your train pipeline as well. I don't see an obvious mistake anywhere, everything seems fine. When you execute the script, is it still the same errors as you posted above?

This part of the error message tells me that the dictionary that holds the mapping from filepaths to transcripts seems to be empty:

_, sr = sf.read(path_list[0])
IndexError: list index out of range

What is shown when you print the result of build_path_to_transcript_dict_ewe()?

NEW ERRORS FOUND: REPO UPDATED: https://github.com/donwany/IMS-Tousan-Ewe.git

Making GPU 0 the only visible device(s). Preparing ... building dataset cache ... /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 114/114 [00:31<00:00, 3.64it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:32<00:00, 3.56it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 114/114 [00:29<00:00, 3.90it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:33<00:00, 3.43it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 114/114 [00:30<00:00, 3.70it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:30<00:00, 3.77it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:30<00:00, 3.72it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:31<00:00, 3.68it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 114/114 [00:31<00:00, 3.65it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:31<00:00, 3.63it/s] pooling results... converting text to tensors... converting speech to tensors... converting waves to tensors... unpacking file list... done! 0it [00:00, ?it/s] Traceback (most recent call last): File "/home/ts75080/Documents/IMS-Toucan/run_training_pipeline.py", line 143, in pipeline_dict[args.pipeline]( File "/home/ts75080/Documents/IMS-Toucan/TrainingPipelines/finetuning_example_simple_ewe.py", line 48, in run train_data = prepare_tts_corpus( File "/home/ts75080/Documents/IMS-Toucan/Utility/corpus_preparation.py", line 53, in prepare_tts_corpus prepare_aligner_corpus( File "/home/ts75080/Documents/IMS-Toucan/Utility/corpus_preparation.py", line 13, in prepare_aligner_corpus return CodecAlignerDataset( File "/home/ts75080/Documents/IMS-Toucan/Architectures/Aligner/CodecAlignerDataset.py", line 43, in init self._build_dataset_cache( File "/home/ts75080/Documents/IMS-Toucan/Architectures/Aligner/CodecAlignerDataset.py", line 199, in _build_dataset_cache raise RuntimeError # something went wrong and there are no datapoints RuntimeError

[Flux9665]

I see, the problem is that you are using stereo audio files and the array is transposed. I will make a commit that checks for this and then fixes the order of the dimensions in the array.

[Flux9665]

If you apply this change to your copy of the repo, it should work:

https://github.com/DigitalPhonetics/IMS-Toucan/commit/e040260197c353b22fe3e41a57e65a3745b4d7b6

[donwany]

If you apply this change to your copy of the repo, it should work:

e040260

added the code and also getting same errors

Making GPU 0 the only visible device(s). Preparing ... building dataset cache ... /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/_distutils_hack/init.py:26: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. Error in loading espeak! Maybe espeak is not installed on your system? Falling back to transphone. /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/modules/transformer.py:306: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") /home/ts75080/miniconda3/envs/ims-toucan/lib/python3.9/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:28<00:00, 3.97it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:29<00:00, 3.90it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 114/114 [00:27<00:00, 4.10it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 114/114 [00:29<00:00, 3.81it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 114/114 [00:28<00:00, 4.04it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 114/114 [00:28<00:00, 4.03it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:28<00:00, 4.04it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:28<00:00, 4.04it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:29<00:00, 3.85it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:29<00:00, 3.88it/s] pooling results... converting text to tensors... converting speech to tensors... converting waves to tensors... unpacking file list... done! 0it [00:00, ?it/s] Traceback (most recent call last): File "/home/ts75080/Documents/IMS-Toucan/run_training_pipeline.py", line 143, in pipeline_dict[args.pipeline]( File "/home/ts75080/Documents/IMS-Toucan/TrainingPipelines/finetuning_example_simple_ewe.py", line 48, in run train_data = prepare_tts_corpus( File "/home/ts75080/Documents/IMS-Toucan/Utility/corpus_preparation.py", line 53, in prepare_tts_corpus prepare_aligner_corpus( File "/home/ts75080/Documents/IMS-Toucan/Utility/corpus_preparation.py", line 13, in prepare_aligner_corpus return CodecAlignerDataset( File "/home/ts75080/Documents/IMS-Toucan/Architectures/Aligner/CodecAlignerDataset.py", line 43, in init self._build_dataset_cache( File "/home/ts75080/Documents/IMS-Toucan/Architectures/Aligner/CodecAlignerDataset.py", line 199, in _build_dataset_cache raise RuntimeError # something went wrong and there are no datapoints RuntimeError

[Flux9665]

If this did not fix the problem, then I am not sure what the cause is. Since I cannot reproduce the issue, it is hard to figure out. The code you have shown looks correct and the fact that the multiprocessed part works indicates that the data is loaded correctly, but then there are no datapoints when the multiprocessed chunks are joined together.

You could try printing wave.shape at the place where we check if the channels are transposed, then we can see if there is a different problem with the audio. Also, to make the logs less messy, you can reduce the number of loading_processes in the Utility/corpus_preparation script to 1.

https://github.com/donwany/IMS-Tousan-Ewe/blob/346a2a32ebfa484ad508418616f3f62ef1615816/Utility/corpus_preparation.py#L17

[Flux9665]

Any update?

[donwany]

I

Any update? It is working based on the screenshot. But got an error at the end. Am yet to debug it.

I printed: print(wave.shape)

See: https://github.com/donwany/IMS-Tousan-Ewe.git