stylewav for testing inference

config_tacotron_gst.json

@@ -77,6 +77,7 @@
         "use_phonemes": true,           // use phonemes instead of raw characters. It is suggested for better pronounciation.
         "phoneme_language": "en-us",     // depending on your target language, pick one from  https://github.com/bootphon/phonemizer#languages
         "text_cleaner": "phoneme_cleaners",
-        "use_speaker_embedding": false // whether to use additional embeddings for separate speakers
+        "use_speaker_embedding": false, // whether to use additional embeddings for separate speakers
+        "style_wav_for_test": null // path to wav for styling the inference tests when using GST
     }
     

train.py

@@ -409,11 +409,13 @@ def evaluate(model, criterion, criterion_st, ap, current_step, epoch):
         test_figures = {}
         print(" | > Synthesizing test sentences")
         speaker_id = 0 if c.use_speaker_embedding else None
+        style_wav = c.get("style_wav_for_test")
         for idx, test_sentence in enumerate(test_sentences):
             try:
                 wav, alignment, decoder_output, postnet_output, stop_tokens = synthesis(
                     model, test_sentence, c, use_cuda, ap,
-                    speaker_id=speaker_id)
+                    speaker_id=speaker_id,
+                    style_wav=style_wav)
                 file_path = os.path.join(AUDIO_PATH, str(current_step))
                 os.makedirs(file_path, exist_ok=True)
                 file_path = os.path.join(file_path,