Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Use fsspec and torch for embedding file IO #1581

Merged
merged 8 commits into from
Jun 1, 2022
Merged

Use fsspec and torch for embedding file IO #1581

Changes from 1 commit
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
15fb20c
Use fsspec and torch for embedding file
erogol May 19, 2022
7eceead
Fixup
erogol May 19, 2022
0111512
Fix load and save files
WeberJulian May 30, 2022
fbb4506
Fix compute embedding script
WeberJulian May 30, 2022
41d86e0
Set use_cuda to true if available
WeberJulian May 30, 2022
9f16700
Add dummy speakers.pth file
WeberJulian May 30, 2022
39f31e3
Make style
WeberJulian May 30, 2022
d7de111
Change default speakers file extension
WeberJulian Jun 1, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions TTS/bin/compute_embeddings.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
import argparse
import os
from argparse import RawTextHelpFormatter
import torch

from tqdm import tqdm

Expand All @@ -22,11 +23,13 @@
parser.add_argument("config_dataset_path", type=str, help="Path to dataset config file.")
parser.add_argument("--output_path", type=str, help="Path for output `pth` or `json` file.", default="speakers.pth")
parser.add_argument("--old_file", type=str, help="Previous embedding file to only compute new audios.", default=None)
parser.add_argument("--use_cuda", type=bool, help="flag to set cuda. Default False", default=False)
parser.add_argument("--disable_cuda", type=bool, help="Flag to disable cuda.", default=False)
Copy link
Member Author

@erogol erogol May 30, 2022 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

To me, this is counter-intuitive but can live with it :)

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I just spent 3h computing phonemes before realizing that it wasn't using the GPU ^^' That's why I changed it to that. Having use_cuda to true by default and then throwing errors if you had no GPU seemed bad...

parser.add_argument("--no_eval", type=bool, help="Do not compute eval?. Default False", default=False)

args = parser.parse_args()

use_cuda = torch.cuda.is_available() and not args.disable_cuda

c_dataset = load_config(args.config_dataset_path)

meta_data_train, meta_data_eval = load_tts_samples(c_dataset.datasets, eval_split=not args.no_eval)
Expand All @@ -40,7 +43,7 @@
encoder_model_path=args.model_path,
encoder_config_path=args.config_path,
d_vectors_file_path=args.old_file,
use_cuda=args.use_cuda,
use_cuda=use_cuda,
)

class_name_key = encoder_manager.encoder_config.class_name_key
Expand Down