Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Set use_cuda to true if available

This commit is contained in:
WeberJulian 2022-05-30 18:58:38 +02:00
parent fbb450616c
commit 41d86e0fe1
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
TTS/bin/compute_embeddings.py
View File

@ -1,6 +1,7 @@
import argparse import argparse
import os import os
from argparse import RawTextHelpFormatter from argparse import RawTextHelpFormatter
import torch
from tqdm import tqdm from tqdm import tqdm
@ -22,11 +23,13 @@ parser.add_argument("config_path", type=str, help="Path to model config file.")
parser.add_argument("config_dataset_path", type=str, help="Path to dataset config file.") 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("--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("--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)
parser.add_argument("--no_eval", type=bool, help="Do not compute eval?. Default False", default=False) parser.add_argument("--no_eval", type=bool, help="Do not compute eval?. Default False", default=False)
args = parser.parse_args() args = parser.parse_args()
use_cuda = torch.cuda.is_available() and not args.disable_cuda
c_dataset = load_config(args.config_dataset_path) 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) meta_data_train, meta_data_eval = load_tts_samples(c_dataset.datasets, eval_split=not args.no_eval)
@ -40,7 +43,7 @@ encoder_manager = SpeakerManager(
encoder_model_path=args.model_path, encoder_model_path=args.model_path,
encoder_config_path=args.config_path, encoder_config_path=args.config_path,
d_vectors_file_path=args.old_file, 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 class_name_key = encoder_manager.encoder_config.class_name_key