Fix API and CI

TTS/tts/layers/xtts/xtts_manager.py

@@ -8,6 +8,14 @@ def __init__(self, speaker_file_path=None):
     def name_to_id(self):
         return self.speakers.keys()
 
+    @property
+    def num_speakers(self):
+        return len(self.name_to_id)
+
+    @property
+    def speaker_names(self):
+        return list(self.name_to_id.keys())
+
 
 class LanguageManager():
     def __init__(self, config):
@@ -16,3 +24,11 @@ def __init__(self, config):
     @property
     def name_to_id(self):
         return self.langs
+
+    @property
+    def num_languages(self):
+        return len(self.name_to_id)
+
+    @property
+    def language_names(self):
+        return list(self.name_to_id)

TTS/tts/models/xtts.py

@@ -379,7 +379,7 @@ def get_conditioning_latents(
 
         return gpt_cond_latents, speaker_embedding
 
-    def synthesize(self, text, config, speaker_wav, language, speaker_id, **kwargs):
+    def synthesize(self, text, config, speaker_wav, language, speaker_id=None, **kwargs):
         """Synthesize speech with the given input text.
 
         Args:
@@ -520,6 +520,8 @@ def inference(
     ):
         language = language.split("-")[0]  # remove the country code
         length_scale = 1.0 / max(speed, 0.05)
+        gpt_cond_latent = gpt_cond_latent.to(self.device)
+        speaker_embedding = speaker_embedding.to(self.device)
         if enable_text_splitting:
             text = split_sentence(text, language, self.tokenizer.char_limits[language])
         else:
@@ -628,6 +630,8 @@ def inference_stream(
     ):
         language = language.split("-")[0]  # remove the country code
         length_scale = 1.0 / max(speed, 0.05)
+        gpt_cond_latent = gpt_cond_latent.to(self.device)
+        speaker_embedding = speaker_embedding.to(self.device)
         if enable_text_splitting:
             text = split_sentence(text, language, self.tokenizer.char_limits[language])
         else: