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

Merge pull request #1044 from WeberJulian/dev 

Fixes before YourTTS merge
This commit is contained in:
Eren Gölge 2022-01-02 11:27:37 +01:00 committed by GitHub
parent 7ef458a59c 9d0a732f97
commit d82fa0536f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 9 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
TTS/tts/datasets/dataset.py
View File

@ -273,7 +273,9 @@ class TTSDataset(Dataset):
item = args[0] item = args[0]
func_args = args[1] func_args = args[1]
text, wav_file, *_ = item text, wav_file, *_ = item
func_args[3] = item[3] if item[3] is not None and item[3] != '':
# If language is specified in dataset, overwrite phoneme_language key
func_args[3] = item[3]
phonemes = TTSDataset._load_or_generate_phoneme_sequence(wav_file, text, *func_args) phonemes = TTSDataset._load_or_generate_phoneme_sequence(wav_file, text, *func_args)
return phonemes return phonemes

8
recipes/vctk/vits/train_vits.py
View File

@ -5,7 +5,7 @@ from TTS.trainer import Trainer, TrainingArgs
from TTS.tts.configs.shared_configs import BaseDatasetConfig from TTS.tts.configs.shared_configs import BaseDatasetConfig
from TTS.tts.configs.vits_config import VitsConfig from TTS.tts.configs.vits_config import VitsConfig
from TTS.tts.datasets import load_tts_samples from TTS.tts.datasets import load_tts_samples
from TTS.tts.models.vits import Vits from TTS.tts.models.vits import Vits, VitsArgs
from TTS.tts.utils.speakers import SpeakerManager from TTS.tts.utils.speakers import SpeakerManager
from TTS.utils.audio import AudioProcessor from TTS.utils.audio import AudioProcessor
@ -31,10 +31,14 @@ audio_config = BaseAudioConfig(
resample=True, resample=True,
) )
vitsArgs = VitsArgs(
use_speaker_embedding=True,
)
config = VitsConfig( config = VitsConfig(
model_args=vitsArgs,
audio=audio_config, audio=audio_config,
run_name="vits_vctk", run_name="vits_vctk",
use_speaker_embedding=True,
batch_size=32, batch_size=32,
eval_batch_size=16, eval_batch_size=16,
batch_group_size=5, batch_group_size=5,