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

Fix #2745 (#2748)

This commit is contained in:
Eren Gölge 2023-07-07 20:23:27 +02:00 committed by GitHub
parent 7b5c8422c8
commit a2984fb435
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
TTS/tts/models/tortoise.py
View File

@ -497,14 +497,14 @@ class Tortoise(BaseTTS):
with torch.no_grad(): with torch.no_grad():
return self.rlg_auto(torch.tensor([0.0])), self.rlg_diffusion(torch.tensor([0.0])) return self.rlg_auto(torch.tensor([0.0])), self.rlg_diffusion(torch.tensor([0.0]))
def synthesize(self, text, config, speaker_id="random", extra_voice_dirs=None, **kwargs): def synthesize(self, text, config, speaker_id="random", voice_dirs=None, **kwargs):
"""Synthesize speech with the given input text. """Synthesize speech with the given input text.
Args: Args:
text (str): Input text. text (str): Input text.
config (TortoiseConfig): Config with inference parameters. config (TortoiseConfig): Config with inference parameters.
speaker_id (str): One of the available speaker names. If `random`, it generates a random speaker. speaker_id (str): One of the available speaker names. If `random`, it generates a random speaker.
extra_voice_dirs (List[str]): List of paths that host reference audio files for speakers. Defaults to None. voice_dirs (List[str]): List of paths that host reference audio files for speakers. Defaults to None.
**kwargs: Inference settings. See `inference()`. **kwargs: Inference settings. See `inference()`.
Returns: Returns:
@ -513,9 +513,9 @@ class Tortoise(BaseTTS):
as latents used at inference. as latents used at inference.
""" """
if extra_voice_dirs is not None: if voice_dirs is not None:
extra_voice_dirs = [extra_voice_dirs] voice_dirs = [voice_dirs]
voice_samples, conditioning_latents = load_voice(speaker_id, extra_voice_dirs) voice_samples, conditioning_latents = load_voice(speaker_id, voice_dirs)
else: else:
voice_samples, conditioning_latents = load_voice(speaker_id) voice_samples, conditioning_latents = load_voice(speaker_id)