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

Update synthesizer.py 

Configurable verbose output
This commit is contained in:
David Martin Rius 2024-03-05 18:36:47 +01:00 committed by GitHub
parent 64fdd0ed8b
commit 275229a876
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 16 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
TTS/utils/synthesizer.py
View File

@ -264,6 +264,7 @@ class Synthesizer(nn.Module):
style_text=None, style_text=None,
reference_wav=None, reference_wav=None,
reference_speaker_name=None, reference_speaker_name=None,
verbose: bool = True,
split_sentences: bool = True, split_sentences: bool = True,
**kwargs, **kwargs,
) -> List[int]: ) -> List[int]:
@ -278,6 +279,7 @@ class Synthesizer(nn.Module):
style_text ([type], optional): transcription of style_wav for Capacitron. Defaults to None. style_text ([type], optional): transcription of style_wav for Capacitron. Defaults to None.
reference_wav ([type], optional): reference waveform for voice conversion. Defaults to None. reference_wav ([type], optional): reference waveform for voice conversion. Defaults to None.
reference_speaker_name ([type], optional): speaker id of reference waveform. Defaults to None. reference_speaker_name ([type], optional): speaker id of reference waveform. Defaults to None.
verbose (bool, optional): print verbose output. Defaults to True.
split_sentences (bool, optional): split the input text into sentences. Defaults to True. split_sentences (bool, optional): split the input text into sentences. Defaults to True.
**kwargs: additional arguments to pass to the TTS model. **kwargs: additional arguments to pass to the TTS model.
Returns: Returns:
@ -294,9 +296,11 @@ class Synthesizer(nn.Module):
if text: if text:
sens = [text] sens = [text]
if split_sentences: if split_sentences:
print(" > Text splitted to sentences.") if verbose:
print(" > Text splitted to sentences.")
sens = self.split_into_sentences(text) sens = self.split_into_sentences(text)
print(sens) if verbose:
print(sens)
# handle multi-speaker # handle multi-speaker
if "voice_dir" in kwargs: if "voice_dir" in kwargs:
@ -420,7 +424,8 @@ class Synthesizer(nn.Module):
self.vocoder_config["audio"]["sample_rate"] / self.tts_model.ap.sample_rate, self.vocoder_config["audio"]["sample_rate"] / self.tts_model.ap.sample_rate,
] ]
if scale_factor[1] != 1: if scale_factor[1] != 1:
print(" > interpolating tts model output.") if verbose:
print(" > interpolating tts model output.")
vocoder_input = interpolate_vocoder_input(scale_factor, vocoder_input) vocoder_input = interpolate_vocoder_input(scale_factor, vocoder_input)
else: else:
vocoder_input = torch.tensor(vocoder_input).unsqueeze(0) # pylint: disable=not-callable vocoder_input = torch.tensor(vocoder_input).unsqueeze(0) # pylint: disable=not-callable
@ -484,7 +489,8 @@ class Synthesizer(nn.Module):
self.vocoder_config["audio"]["sample_rate"] / self.tts_model.ap.sample_rate, self.vocoder_config["audio"]["sample_rate"] / self.tts_model.ap.sample_rate,
] ]
if scale_factor[1] != 1: if scale_factor[1] != 1:
print(" > interpolating tts model output.") if verbose:
print(" > interpolating tts model output.")
vocoder_input = interpolate_vocoder_input(scale_factor, vocoder_input) vocoder_input = interpolate_vocoder_input(scale_factor, vocoder_input)
else: else:
vocoder_input = torch.tensor(vocoder_input).unsqueeze(0) # pylint: disable=not-callable vocoder_input = torch.tensor(vocoder_input).unsqueeze(0) # pylint: disable=not-callable
@ -497,9 +503,10 @@ class Synthesizer(nn.Module):
waveform = waveform.numpy() waveform = waveform.numpy()
wavs = waveform.squeeze() wavs = waveform.squeeze()
# compute stats if verbose:
process_time = time.time() - start_time # compute stats
audio_time = len(wavs) / self.tts_config.audio["sample_rate"] process_time = time.time() - start_time
print(f" > Processing time: {process_time}") audio_time = len(wavs) / self.tts_config.audio["sample_rate"]
print(f" > Real-time factor: {process_time / audio_time}") print(f" > Processing time: {process_time}")
print(f" > Real-time factor: {process_time / audio_time}")
return wavs return wavs