w2v2-speaker

w2v2-speaker copied to clipboard

Thanks for your code,it helped me a lot,but I tried to use Wav2Vec2 model and got error as following: `RuntimeError: Expected 2D (unbatched) or 3D (batched) input to conv1d, but...

evelynlee999

Can I use the code by windows os? Or just linux can run?

1

hello, i find that this project is using in linux os, and when i try to use it by windows os, there throw a problem shows like below.  UserWarning:...

angryman123

作者您好，在阅读readme中关于下载meta数据的描述，文中是否应该修改成使用download_voxceleb_meta.sh，即 You should also download the meta files of voxceleb. You can use preparation_scripts/download_voxceleb_meta.sh to download them to the expected location $DATA_FOLDER/voxceleb_meta

angryman123

releasing fine-tuned model

5

Hello, thanks for your work and code, which help my research a lot. I wonder if you could provide the fine-tuned model?

GuangkeChen

How can i get fixed length embedding for each audio?

1

Is there any direct function that I can call to extract fixed-length embedding for each audio sample using the pre-trained model?

iMayK

tasks of speech synthesis

1

Hello, what should I do if I want to use your model results as the speaker ID for the speech synthesis project? Can you publish your training model

tuntun990606

Can't install dependencies with Poetry

2

Hi, I'm having some trouble installing the dependencies with Poetry. I always get this error when Poetry is installing fairseq: ``` • Installing fairseq (0.10.2): Failed ChefBuildError Backend subprocess exited...

atosborges00

MKL_NUM_THREADS=1 CUDA_VISIBLE_DEVICES=1 python run.py +experiment=speaker_ecapa_tdnn tune_model=True data/module=dogbark trainer.auto_lr_find=auto_lr_find tune_iterations=5000 /home/arthur/.conda/envs/w2v2/lib/python3.8/site-packages/pytorch_lightning/core/decorators.py:65: LightningDeprecationWarning: The `@auto_move_data` decorator is deprecated in v1.3 and will be removed in v1.5. Please use `trainer.predict` instead for inference....

Arthurwyf

MKL_NUM_THREADS=1 CUDA_VISIBLE_DEVICES=1 python run.py +experiment=speaker_ecapa_tdnn tune_model=True data/module=dogbark trainer.auto_lr_find=auto_lr_find tune_iterations=5000 /home/arthur/.conda/envs/w2v2/lib/python3.8/site-packages/pytorch_lightning/core/decorators.py:65: LightningDeprecationWarning: The `@auto_move_data` decorator is deprecated in v1.3 and will be removed in v1.5. Please use `trainer.predict` instead for inference....

Arthurwyf

First of all, thanks for sharing the code of your paper. I would like to train the aam model on my own data. What should be the configuration of my...

zivrafa