mirror of
https://github.com/wassname/TTS.git
synced 2026-09-11 12:00:24 +08:00
change stop conditioning
This commit is contained in:
+9
-6
@@ -125,8 +125,8 @@ class Attention(nn.Module):
|
||||
self._mask_value = -float("inf")
|
||||
self.windowing = windowing
|
||||
if self.windowing:
|
||||
self.win_back = 3
|
||||
self.win_front = 6
|
||||
self.win_back = 1
|
||||
self.win_front = 3
|
||||
self.win_idx = None
|
||||
self.norm = norm
|
||||
|
||||
@@ -394,7 +394,8 @@ class Decoder(nn.Module):
|
||||
|
||||
self.attention_layer.init_win_idx()
|
||||
outputs, stop_tokens, alignments, t = [], [], [], 0
|
||||
stop_flags = [False, False, False]
|
||||
stop_flags = [True, False, False]
|
||||
stop_count = 0
|
||||
while True:
|
||||
memory = self.prenet(memory)
|
||||
mel_output, stop_token, alignment = self.decode(memory)
|
||||
@@ -404,10 +405,12 @@ class Decoder(nn.Module):
|
||||
alignments += [alignment]
|
||||
|
||||
stop_flags[0] = stop_flags[0] or stop_token > 0.5
|
||||
stop_flags[1] = stop_flags[1] or (alignment[0, -2:].sum() > 0.5 and t > inputs.shape[1])
|
||||
stop_flags[2] = t > inputs.shape[1]
|
||||
stop_flags[1] = stop_flags[1] or (alignment[0, -2:].sum() > 0.8 and t > inputs.shape[1])
|
||||
stop_flags[2] = t > inputs.shape[1] * 2
|
||||
if all(stop_flags):
|
||||
break
|
||||
stop_count += 1
|
||||
if stop_count > 10:
|
||||
break
|
||||
elif len(outputs) == self.max_decoder_steps:
|
||||
print(" | > Decoder stopped with 'max_decoder_steps")
|
||||
break
|
||||
|
||||
Reference in New Issue
Block a user