Update synthesis for the new API

This commit is contained in:
Eren Gölge
2022-02-25 10:48:03 +01:00
parent 4e83bf3968
commit d8ec7086b6
+2 -7
View File
@@ -113,8 +113,6 @@ def synthesis(
text,
CONFIG,
use_cuda,
ap,
tokenizer,
speaker_id=None,
style_wav=None,
use_griffin_lim=False,
@@ -139,9 +137,6 @@ def synthesis(
use_cuda (bool):
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 passed to the speaker embedding layer in multi-speaker model. Defaults to None.
@@ -169,10 +164,10 @@ def synthesis(
if isinstance(style_wav, dict):
style_mel = style_wav
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
text_inputs = np.asarray(
tokenizer.text_to_ids(text),
model.tokenizer.text_to_ids(text),
dtype=np.int32,
)
# pass tensors to backend