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 `synthesis` for the new API

This commit is contained in:
Eren Gölge 2021-11-24 18:41:21 +01:00
parent 4e83bf3968
commit d8ec7086b6
1 changed files with 2 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
TTS/tts/utils/synthesis.py
View File

@ -113,8 +113,6 @@ def synthesis(
text, text,
CONFIG, CONFIG,
use_cuda, use_cuda,
ap,
tokenizer,
speaker_id=None, speaker_id=None,
style_wav=None, style_wav=None,
use_griffin_lim=False, use_griffin_lim=False,
@ -139,9 +137,6 @@ def synthesis(
use_cuda (bool): use_cuda (bool):
Enable/disable CUDA. Enable/disable CUDA.
ap (TTS.tts.utils.audio.AudioProcessor):
The audio processor for extracting features and pre/post-processing audio.
speaker_id (int): speaker_id (int):
Speaker ID passed to the speaker embedding layer in multi-speaker model. Defaults to None. Speaker ID passed to the speaker embedding layer in multi-speaker model. Defaults to None.
@ -169,10 +164,10 @@ def synthesis(
if isinstance(style_wav, dict): if isinstance(style_wav, dict):
style_mel = style_wav style_mel = style_wav
else: else:
style_mel = compute_style_mel(style_wav, ap, cuda=use_cuda) style_mel = compute_style_mel(style_wav, model.ap, cuda=use_cuda)
# convert text to sequence of token IDs # convert text to sequence of token IDs
text_inputs = np.asarray( text_inputs = np.asarray(
tokenizer.text_to_ids(text), model.tokenizer.text_to_ids(text),
dtype=np.int32, dtype=np.int32,
) )
# pass tensors to backend # pass tensors to backend