mirror of
https://github.com/SWivid/F5-TTS.git
synced 2026-01-14 05:57:41 -08:00
Update socket.py
[edit] adjusting mel_spec_type on load_model use case
This commit is contained in:
@@ -19,10 +19,14 @@ class TTSStreamingProcessor:
|
||||
|
||||
# Load the model using the provided checkpoint and vocab files
|
||||
self.model = load_model(
|
||||
DiT,
|
||||
dict(dim=1024, depth=22, heads=16, ff_mult=2, text_dim=512, conv_layers=4),
|
||||
ckpt_file,
|
||||
vocab_file,
|
||||
model_cls=DiT,
|
||||
model_cfg=dict(dim=1024, depth=22, heads=16, ff_mult=2, text_dim=512, conv_layers=4),
|
||||
ckpt_path=ckpt_file,
|
||||
mel_spec_type="vocos", # or "bigvgan" depending on vocoder
|
||||
vocab_file=vocab_file,
|
||||
ode_method="euler",
|
||||
use_ema=True,
|
||||
device=self.device
|
||||
).to(self.device, dtype=dtype)
|
||||
|
||||
# Load the vocoder
|
||||
|
||||
Reference in New Issue
Block a user