zaebee

/

speecht5_tts_common_ru

like 4

Trying to use in one of out projects, getting this error:

(InfernTTSActor pid=434864)   File "/home/sobomax/projects/Infernos/HelloSippyTTSRT/HelloSippyRT.py", line 247, in __init__
(InfernTTSActor pid=434864)     self.processor = SpeechT5Processor.from_pretrained(model)
(InfernTTSActor pid=434864)                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(InfernTTSActor pid=434864)   File "/home/sobomax/miniconda3/envs/tinygrad/lib/python3.11/site-packages/transformers/processing_utils.py", line 465, in from_pretrained
(InfernTTSActor pid=434864)     args = cls._get_arguments_from_pretrained(pretrained_model_name_or_path, **kwargs)
(InfernTTSActor pid=434864)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(InfernTTSActor pid=434864)   File "/home/sobomax/miniconda3/envs/tinygrad/lib/python3.11/site-packages/transformers/processing_utils.py", line 511, in _get_arguments_from_pretrained
(InfernTTSActor pid=434864)     args.append(attribute_class.from_pretrained(pretrained_model_name_or_path, **kwargs))
(InfernTTSActor pid=434864)                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(InfernTTSActor pid=434864)   File "/home/sobomax/miniconda3/envs/tinygrad/lib/python3.11/site-packages/transformers/feature_extraction_utils.py", line 372, in from_pretrained
(InfernTTSActor pid=434864)     feature_extractor_dict, kwargs = cls.get_feature_extractor_dict(pretrained_model_name_or_path, **kwargs)
(InfernTTSActor pid=434864)                                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(InfernTTSActor pid=434864)   File "/home/sobomax/miniconda3/envs/tinygrad/lib/python3.11/site-packages/transformers/feature_extraction_utils.py", line 497, in get_feature_extractor_dict
(InfernTTSActor pid=434864)     resolved_feature_extractor_file = cached_file(
(InfernTTSActor pid=434864)                                       ^^^^^^^^^^^^
(InfernTTSActor pid=434864)   File "/home/sobomax/miniconda3/envs/tinygrad/lib/python3.11/site-packages/transformers/utils/hub.py", line 452, in cached_file
(InfernTTSActor pid=434864)     raise EnvironmentError(
(InfernTTSActor pid=434864) OSError: zaebee/speecht5_tts_common_ru does not appear to have a file named preprocessor_config.json. Checkout 'https://huggingface.co/zaebee/speecht5_tts_common_ru/main' for available files.

Some other SeechT5 fine-tunes don't have this issue, i.e.: https://huggingface.co/Sandiago21/speecht5_finetuned_voxpopuli_it, https://huggingface.co/JFuellem/speecht5_finetuned_voxpopuli_de on HF.