Update vits.py

k2-fsa · Oct 22, 2024 · 32cdbdf · 32cdbdf
1 parent 3ac1331
commit 32cdbdf
Showing 1 changed file with 3 additions and 0 deletions.
diff --git a/egs/ljspeech/TTS/vits/vits.py b/egs/ljspeech/TTS/vits/vits.py
@@ -623,6 +623,7 @@ def inference_batch(
         text_lengths: torch.Tensor,
         sids: Optional[torch.Tensor] = None,
         spembs: Optional[torch.Tensor] = None,
+        lids: Optional[torch.Tensor] = None,
         durations: Optional[torch.Tensor] = None,
         noise_scale: float = 0.667,
         noise_scale_dur: float = 0.8,
@@ -637,6 +638,7 @@ def inference_batch(
             text_lengths (Tensor): Input text index tensor (B,).
             sids (Tensor): Speaker index tensor (B,).
             spembs (Optional[Tensor]): Speaker embedding tensor (B, spk_embed_dim).
+            lids (Tensor): Language index tensor (B,).
             noise_scale (float): Noise scale value for flow.
             noise_scale_dur (float): Noise scale value for duration predictor.
             alpha (float): Alpha parameter to control the speed of generated speech.
@@ -653,6 +655,7 @@ def inference_batch(
             text_lengths=text_lengths,
             sids=sids,
             spembs=spembs,
+            lids=lids,
             noise_scale=noise_scale,
             noise_scale_dur=noise_scale_dur,
             alpha=alpha,