neonbjb / tortoise-tts

A multi-voice TTS system trained with an emphasis on quality
Apache License 2.0
12.89k stars 1.78k forks source link

py:17: WavFileWarning: Chunk (non-data) not understood, skipping it. #309

Open FurkanGozukara opened 1 year ago

FurkanGozukara commented 1 year ago

I am providing wav files but it is giving me this warning

Any ideas why? The sound is not like me :/

Here my command and results

(env) D:\86 se courses youtube kanali\tortoise-tts>python tortoise/do_tts.py --text "So if you use the latest framework of Microsoft .NET platform it is core and it supports Mac OS and Linux as well for console applications." --voice="myvoices" --preset fast D:\86 se courses youtube kanali\tortoise-tts\tortoise\utils\audio.py:17: WavFileWarning: Chunk (non-data) not understood, skipping it. sampling_rate, data = read(full_path) Generating autoregressive samples.. 100%|██████████████████████████████████████████████████████████████████████████████████| 12/12 [01:53<00:00, 9.42s/it] Computing best candidates using CLVP 100%|██████████████████████████████████████████████████████████████████████████████████| 12/12 [00:05<00:00, 2.32it/s] Transforming autoregressive outputs into audio.. 100%|██████████████████████████████████████████████████████████████████████████████████| 80/80 [00:29<00:00, 2.71it/s] 100%|██████████████████████████████████████████████████████████████████████████████████| 80/80 [00:31<00:00, 2.56it/s] 100%|██████████████████████████████████████████████████████████████████████████████████| 80/80 [00:32<00:00, 2.46it/s]

example wav file : https://drive.google.com/file/d/1odxPpTJePQfMHxiO2jdeuYA7zxgvWg4c/view?usp=sharing

neonbjb commented 1 year ago

Don't worry about those warnings, they are innocuous.

Tortoise is hit or miss for voice cloning. It doesn't work great for really unique voices.