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 G??lge 2023-11-06 19:02:09 +01:00
parent 46940cb64b
commit b702b39b52
6 changed files with 16 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
TTS/tts/models/base_tacotron.py
View File

@ -252,7 +252,12 @@ class BaseTacotron(BaseTTS):
def compute_capacitron_VAE_embedding(self, inputs, reference_mel_info, text_info=None, speaker_embedding=None): def compute_capacitron_VAE_embedding(self, inputs, reference_mel_info, text_info=None, speaker_embedding=None):
"""Capacitron Variational Autoencoder""" """Capacitron Variational Autoencoder"""
(VAE_outputs, posterior_distribution, prior_distribution, capacitron_beta,) = self.capacitron_vae_layer( (
VAE_outputs,
posterior_distribution,
prior_distribution,
capacitron_beta,
) = self.capacitron_vae_layer(
reference_mel_info, reference_mel_info,
text_info, text_info,
speaker_embedding, # pylint: disable=not-callable speaker_embedding, # pylint: disable=not-callable

7
TTS/tts/models/tortoise.py
View File

@ -676,7 +676,12 @@ class Tortoise(BaseTTS):
), "Too much text provided. Break the text up into separate segments and re-try inference." ), "Too much text provided. Break the text up into separate segments and re-try inference."
if voice_samples is not None: if voice_samples is not None:
(auto_conditioning, diffusion_conditioning, _, _,) = self.get_conditioning_latents( (
auto_conditioning,
diffusion_conditioning,
_,
_,
) = self.get_conditioning_latents(
voice_samples, voice_samples,
return_mels=True, return_mels=True,
latent_averaging_mode=latent_averaging_mode, latent_averaging_mode=latent_averaging_mode,

4
recipes/ljspeech/xtts_v1/train_gpt_xtts.py
View File

@ -97,9 +97,7 @@ def main():
use_ne_hifigan=True, # if it is true it will keep the non-enhanced keys on the output checkpoint use_ne_hifigan=True, # if it is true it will keep the non-enhanced keys on the output checkpoint
) )
# define audio config # define audio config
audio_config = XttsAudioConfig( audio_config = XttsAudioConfig(sample_rate=22050, dvae_sample_rate=22050, output_sample_rate=24000)
sample_rate=22050, dvae_sample_rate=22050, output_sample_rate=24000
)
# training parameters config # training parameters config
config = GPTTrainerConfig( config = GPTTrainerConfig(
output_path=OUT_PATH, output_path=OUT_PATH,

4
recipes/ljspeech/xtts_v2/train_gpt_xtts.py
View File

@ -98,9 +98,7 @@ def main():
gpt_use_perceiver_resampler=True, gpt_use_perceiver_resampler=True,
) )
# define audio config # define audio config
audio_config = XttsAudioConfig( audio_config = XttsAudioConfig(sample_rate=22050, dvae_sample_rate=22050, output_sample_rate=24000)
sample_rate=22050, dvae_sample_rate=22050, output_sample_rate=24000
)
# training parameters config # training parameters config
config = GPTTrainerConfig( config = GPTTrainerConfig(
output_path=OUT_PATH, output_path=OUT_PATH,

4
tests/xtts_tests/test_xtts_gpt_train.py
View File

@ -88,9 +88,7 @@ model_args = GPTArgs(
gpt_stop_audio_token=8193, gpt_stop_audio_token=8193,
use_ne_hifigan=True, use_ne_hifigan=True,
) )
audio_config = XttsAudioConfig( audio_config = XttsAudioConfig(sample_rate=22050, dvae_sample_rate=22050, output_sample_rate=24000)
sample_rate=22050, dvae_sample_rate=22050, output_sample_rate=24000
)
config = GPTTrainerConfig( config = GPTTrainerConfig(
epochs=1, epochs=1,
output_path=OUT_PATH, output_path=OUT_PATH,

4
tests/xtts_tests/test_xtts_v2-0_gpt_train.py
View File

@ -88,9 +88,7 @@ model_args = GPTArgs(
gpt_use_perceiver_resampler=True, gpt_use_perceiver_resampler=True,
use_ne_hifigan=True, use_ne_hifigan=True,
) )
audio_config = XttsAudioConfig( audio_config = XttsAudioConfig(sample_rate=22050, dvae_sample_rate=22050, output_sample_rate=24000)
sample_rate=22050, dvae_sample_rate=22050, output_sample_rate=24000
)
config = GPTTrainerConfig( config = GPTTrainerConfig(
epochs=1, epochs=1,
output_path=OUT_PATH, output_path=OUT_PATH,