Open ducpham611 opened 6 months ago
I have the same problem when using the local English-language model TTS en_v3. Have you found a solution?
@RomiconEZ I haven't found any solution for that. It seems like he hadn't updated this project for a long time. Sorry I couldn't help you anything.
I just uncomment the silero tts in run.py and it give me this error. If possible, can you tell me how to fix this, thank you. Traceback (most recent call last): File "G:\Test AI Vtuber\AI-Waifu-Vtuber\run.py", line 248, in.multi_acc_v3_package.py", line 366, in save_wav
File ".multi_acc_v3_package.py", line 316, in apply_tts
File ".multi_acc_v3_package.py", line 63, in prepare_tts_model_input
File ".multi_acc_v3_package.py", line 91, in process_simple_text
ValueError
record_audio() File "G:\Test AI Vtuber\AI-Waifu-Vtuber\run.py", line 68, in record_audio
transcribe_audio("input.wav") File "G:\Test AI Vtuber\AI-Waifu-Vtuber\run.py", line 87, in transcribe_audio openai_answer() File "G:\Test AI Vtuber\AI-Waifu-Vtuber\run.py", line 120, in openai_answer translate_text(message) File "G:\Test AI Vtuber\AI-Waifu-Vtuber\run.py", line 206, in translate_text silero_tts(tts_en, "en", "v3_en", "en_21") File "G:\Test AI Vtuber\AI-Waifu-Vtuber\utils\TTS.py", line 23, in silero_tts audio_paths = model.save_wav(text=tts, ^^^^^^^^^^^^^^^^^^^^^^^^ File "