updated error messages

long_audio_transcribe.py

@@ -61,7 +61,9 @@ if __name__ == "__main__":
             # trimmed_wav_seg = librosa.effects.trim(wav_seg.squeeze().numpy())
             # trimmed_wav_seg = torch.tensor(trimmed_wav_seg[0]).unsqueeze(0)
             torchaudio.save(savepth, wav_seg, 22050, channels_first=True)
-
+    if len(speaker_annos) == 0:
+        print("Warning: no long audios & videos found, this IS expected if you have only uploaded short audios")
+        print("this IS NOT expected if you have uploaded any long audios, videos or video links. Please check your file structure or make sure your audio/video language is supported.")
     with open("long_character_anno.txt", 'w', encoding='utf-8') as f:
         for line in speaker_annos:
             f.write(line)

preprocess_v2.py

@@ -24,7 +24,7 @@ if __name__ == "__main__":
         path, speaker, text = line.split("|")
         if speaker not in speakers:
             speakers.append(speaker)
-    assert (len(speakers) != 0), "no speaker found"
+    assert (len(speakers) != 0), "No audio file found. Please check your uploaded file structure."
     # Source 3 (Optional): sampled audios as extra training helpers
     if args.add_auxiliary_data:
         with open("sampled_audio4ft.txt", 'r', encoding='utf-8') as f:

short_audio_transcribe.py

@@ -87,6 +87,9 @@ if __name__ == "__main__":
     #     cleaned_text += "\n" if not cleaned_text.endswith("\n") else ""
     #     speaker_annos[i] = path + "|" + sid + "|" + cleaned_text
     # write into annotation
+    if len(speaker_annos) == 0:
+        print("Warning: no short audios found, this IS expected if you have only uploaded long audios, videos or video links.")
+        print("this IS NOT expected if you have uploaded a zip file of short audios. Please check your file structure or make sure your audio language is supported.")
     with open("short_character_anno.txt", 'w', encoding='utf-8') as f:
         for line in speaker_annos:
             f.write(line)