Closed thorstenMueller closed 4 years ago
After chatting with Neil (@nmstoker) and experimenting on my local environment i learned the following lessons which might be helpful for others.
Using the following prepared datasets/files combination worked for me for compute embeddings:
model/config template (libretts_360): https://drive.google.com/drive/folders/1CwXxwm0qKk2lcPL_4EQDirD8XMyvHIqR
raw wav/metadata: https://openslr.org/60/
Extract tgz files
Adjust config.json (downloaded template from googledrive) for your local environment path
Exec "compute_embeddings.py" with required params (will be executed if missing)
During process run several .npy files will be created in subdirectories under
If you see a growing number of .npy files you're on a good way.
After process has finished it's time to take a look to the jupyter notebook "PlotUmapLibriTTS.ipynb" under "/TTS/speaker_encoder/notebooks/"
Modify path vars in notebook to match your environment
Run jupyter notebook step by step
I got the error about missing "TTS" module directly in first block which could be solved by copying the notebook into the parent folder of "TTS".
At the end of notebook execution the cluster-graph was successfully generated.
Finally Neil told me a look to Resemblyzer (https://github.com/resemble-ai/Resemblyzer#what-can-i-do-with-this-package) might be helpful for analyzing quality of dataset.
Hello @thorstenMueller I am trying to run the compute_embeddings.py but, I get the following error
Traceback (most recent call last): File "TTS/bin/compute_embeddings.py", line 100, in <module> model.load_state_dict(torch.load(args.model_path)['model']) File "/home/manuel_servex/tmp/tts-train-venv/lib/python3.7/site-packages/torch/serialization.py", line 579, in load with _open_file_like(f, 'rb') as opened_file: File "/home/manuel_servex/tmp/tts-train-venv/lib/python3.7/site-packages/torch/serialization.py", line 230, in _open_file_like return _open_file(name_or_buffer, mode) File "/home/manuel_servex/tmp/tts-train-venv/lib/python3.7/site-packages/torch/serialization.py", line 211, in __init__ super(_open_file, self).__init__(open(name, mode)) IsADirectoryError: [Errno 21] Is a directory:
From what I understand it is the model_path parameter, which must be a model, if so, is it necessary to do a previous step? or how can I execute the compute_embeddings. I would appreciate it if you could provide a quick guide.
This project is not maintained anymore. Feel free to move over Coqui-TTS https://github.com/coqui-ai/TTS which is the actively developed hard fork.
Hello dear community.
Thanks to the great support by @nmstoker i try to run compute_embeddings.py (master branch) on a ljspeech dataset in a venv environment:
The process fails directly with following error:
dataset and config source
Split metadata.csv (even it shouldn't be needed for compute embeddings):
config.json:
General information:
Output from pip3 list: