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

Make style

This commit is contained in:
Eren Gölge 2022-05-03 13:53:06 +02:00 committed by Eren G??lge
parent b73b445278
commit d832d6b08a
3 changed files with 6 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
TTS/tts/models/vits.py
View File

@ -204,6 +204,7 @@ def wav_to_mel(y, n_fft, num_mels, sample_rate, hop_length, win_length, fmin, fm
# CONFIGS # CONFIGS
############################# #############################
class VitsAudioConfig(Coqpit): class VitsAudioConfig(Coqpit):
sample_rate: int = 22050 sample_rate: int = 22050
win_length: int = 1024 win_length: int = 1024
@ -212,6 +213,7 @@ class VitsAudioConfig(Coqpit):
mel_fmin: int = 0 mel_fmin: int = 0
mel_fmax: int = None mel_fmax: int = None
############################## ##############################
# DATASET # DATASET
############################## ##############################

9
recipes/ljspeech/vits_tts/train_vits.py
View File

@ -14,12 +14,7 @@ dataset_config = BaseDatasetConfig(
name="ljspeech", meta_file_train="metadata.csv", path=os.path.join(output_path, "../LJSpeech-1.1/") name="ljspeech", meta_file_train="metadata.csv", path=os.path.join(output_path, "../LJSpeech-1.1/")
) )
audio_config = VitsAudioConfig( audio_config = VitsAudioConfig(
sample_rate=22050, sample_rate=22050, win_length=1024, hop_length=256, num_mels=80, mel_fmin=0, mel_fmax=None
win_length=1024,
hop_length=256,
num_mels=80,
mel_fmin=0,
mel_fmax=None
) )
config = VitsConfig( config = VitsConfig(
@ -43,7 +38,7 @@ config = VitsConfig(
mixed_precision=True, mixed_precision=True,
output_path=output_path, output_path=output_path,
datasets=[dataset_config], datasets=[dataset_config],
cudnn_benchmark=False cudnn_benchmark=False,
) )
# INITIALIZE THE AUDIO PROCESSOR # INITIALIZE THE AUDIO PROCESSOR

9
recipes/vctk/vits/train_vits.py
View File

@ -17,12 +17,7 @@ dataset_config = BaseDatasetConfig(
audio_config = VitsAudioConfig( audio_config = VitsAudioConfig(
sample_rate=22050, sample_rate=22050, win_length=1024, hop_length=256, num_mels=80, mel_fmin=0, mel_fmax=None
win_length=1024,
hop_length=256,
num_mels=80,
mel_fmin=0,
mel_fmax=None
) )
vitsArgs = VitsArgs( vitsArgs = VitsArgs(
@ -52,7 +47,7 @@ config = VitsConfig(
max_text_len=325, # change this if you have a larger VRAM than 16GB max_text_len=325, # change this if you have a larger VRAM than 16GB
output_path=output_path, output_path=output_path,
datasets=[dataset_config], datasets=[dataset_config],
cudnn_benchmark=False cudnn_benchmark=False,
) )
# INITIALIZE THE AUDIO PROCESSOR # INITIALIZE THE AUDIO PROCESSOR