Problem while extracting Voice embeddings
Author: mukherjeesougata-erosCreated Aug 7, 2025Updated Aug 11, 2025
LabelsBug
I am trying to extract the voice embeddings using the notebook that is provided here. I have set input_feature = "wavlm" and architecture = "ecapa". However, when I run the cell containing the following code snippet:-
import numpy as np
from espnet2.bin.spk_inference import Speech2Embedding
speech2embedding = Speech2Embedding.from_pretrained(model_tag=model_tag, device="cuda")I am encountering error which is as follows:-
ModuleNotFoundError Traceback (most recent call last)
File ~/anaconda3/envs/se/lib/python3.10/site-packages/transformers/utils/import_utils.py:2292, in _LazyModule.__getattr__(self, name)
[2291](https://vscode-remote+ssh-002dremote-002b217-002e18-002e52-002e7.vscode-resource.vscode-cdn.net/data0/Senior-Engineer-audio/Data_study/~/anaconda3/envs/se/lib/python3.10/site-packages/transformers/utils/import_utils.py:2291) try:
-> [2292](https://vscode-remote+ssh-002dremote-002b217-002e18-002e52-002e7.vscode-resource.vscode-cdn.net/data0/Senior-Engineer-audio/Data_study/~/anaconda3/envs/se/lib/python3.10/site-packages/transformers/utils/import_utils.py:2292) module = self._get_module(self._class_to_module[name])
[2293](https://vscode-remote+ssh-002dremote-002b217-002e18-002e52-002e7.vscode-resource.vscode-cdn.net/data0/Senior-Engineer-audio/Data_study/~/anaconda3/envs/se/lib/python3.10/site-packages/transformers/utils/import_utils.py:2293) value = getattr(module, name)
File ~/anaconda3/envs/se/lib/python3.10/site-packages/transformers/utils/import_utils.py:2322, in _LazyModule._get_module(self, module_name)
[2321](https://vscode-remote+ssh-002dremote-002b217-002e18-002e52-002e7.vscode-resource.vscode-cdn.net/data0/Senior-Engineer-audio/Data_study/~/anaconda3/envs/se/lib/python3.10/site-packages/transformers/utils/import_utils.py:2321) except Exception as e:
-> [2322](https://vscode-remote+ssh-002dremote-002b217-002e18-002e52-002e7.vscode-resource.vscode-cdn.net/data0/Senior-Engineer-audio/Data_study/~/anaconda3/envs/se/lib/python3.10/site-packages/transformers/utils/import_utils.py:2322) raise e
File ~/anaconda3/envs/se/lib/python3.10/site-packages/transformers/utils/import_utils.py:2320, in _LazyModule._get_module(self, module_name)
[2319](https://vscode-remote+ssh-002dremote-002b217-002e18-002e52-002e7.vscode-resource.vscode-cdn.net/data0/Senior-Engineer-audio/Data_study/~/anaconda3/envs/se/lib/python3.10/site-packages/transformers/utils/import_utils.py:2319) try:
-> [2320](https://vscode-remote+ssh-002dremote-002b217-002e18-002e52-002e7.vscode-resource.vscode-cdn.net/data0/Senior-Engineer-audio/Data_study/~/anaconda3/envs/se/lib/python3.10/site-packages/transformers/utils/import_utils.py:2320) return importlib.import_module("." + module_name, self.__name__)
[2321](https://vscode-remote+ssh-002dremote-002b217-002e18-002e52-002e7.vscode-resource.vscode-cdn.net/data0/Senior-Engineer-audio/Data_study/~/anaconda3/envs/se/lib/python3.10/site-packages/transformers/utils/import_utils.py:2321) except Exception as e:
File ~/anaconda3/envs/se/lib/python3.10/importlib/__init__.py:126, in import_module(name, package)
[125](https://vscode-remote+ssh-002dremote-002b217-002e18-002e52-002e7.vscode-resource.vscode-cdn.net/data0/Senior-Engineer-audio/Data_study/~/anaconda3/envs/se/lib/python3.10/importlib/__init__.py:125) level += 1
--> [126](https://vscode-remote+ssh-002dremote-002b217-002e18-002e52-002e7.vscode-resource.vscode-cdn.net/data0/Senior-Engineer-audio/Data_study/~/anaconda3/envs/se/lib/python3.10/importlib/__init__.py:126) return _bootstrap._gcd_import(name[level:], package, level)
File <frozen importlib._bootstrap>:1050, in _gcd_import(name, package, level)
File <frozen importlib._bootstrap>:1027, in _find_and_load(name, import_)
File <frozen importlib._bootstrap>:1006, in _find_and_load_unlocked(name, import_)
...
[2297](https://vscode-remote+ssh-002dremote-002b217-002e18-002e52-002e7.vscode-resource.vscode-cdn.net/data0/Senior-Engineer-audio/Data_study/~/anaconda3/envs/se/lib/python3.10/site-packages/transformers/utils/import_utils.py:2297) ) from e
[2299](https://vscode-remote+ssh-002dremote-002b217-002e18-002e52-002e7.vscode-resource.vscode-cdn.net/data0/Senior-Engineer-audio/Data_study/~/anaconda3/envs/se/lib/python3.10/site-packages/transformers/utils/import_utils.py:2299) elif name in self._modules:
[2300](https://vscode-remote+ssh-002dremote-002b217-002e18-002e52-002e7.vscode-resource.vscode-cdn.net/data0/Senior-Engineer-audio/Data_study/~/anaconda3/envs/se/lib/python3.10/site-packages/transformers/utils/import_utils.py:2300) try:
ModuleNotFoundError: Could not import module 'HubertModel'. Are this object's requirements defined correctly?Source: espnet/espnet