python 3.13 - ChatTTS transformer text to speech

Question

I'm trying to use ChatTTS which uses Torch. I installed it via the Pycharm packages repository (PIP) with no errors.

But when I run the main webpages basic example code.

import ChatTTS
import torch
import torchaudio

chat = ChatTTS.Chat()
chat.load(compile=False) # Set to True for better performance

texts = ["PUT YOUR 1st TEXT HERE", "PUT YOUR 2nd TEXT HERE"]

wavs = chat.infer(texts)

for i in range(len(wavs)):
    """
    In some versions of torchaudio, the first line works but in other versions, so does the second line.
    """
    try:
        torchaudio.save(f"basic_output{i}.wav", torch.from_numpy(wavs[i]).unsqueeze(0), 24000)
    except:
        torchaudio.save(f"basic_output{i}.wav", torch.from_numpy(wavs[i]), 24000)

It returns the following error,

Traceback (most recent call last):
  File "D:\GOOD\Coding\.Coding_Projects\Composite_media\Text to Speech\Audiobook_Maker\test3.py", line 8, in <module>
    import ChatTTS
  File "C:\Users\User\AppData\Local\Programs\Python\Python313\Lib\site-packages\ChatTTS\__init__.py", line 1, in <module>
    from .core import Chat
  File "C:\Users\User\AppData\Local\Programs\Python\Python313\Lib\site-packages\ChatTTS\core.py", line 17, in <module>
    from .model import DVAE, Embed, GPT, gen_logits, Tokenizer, Speaker
  File "C:\Users\User\AppData\Local\Programs\Python\Python313\Lib\site-packages\ChatTTS\model\__init__.py", line 6, in <module>
    from .tokenizer import Tokenizer
  File "C:\Users\User\AppData\Local\Programs\Python\Python313\Lib\site-packages\ChatTTS\model\tokenizer.py", line 16, in <module>
    class Tokenizer:
    ...<121 lines>...
            )
  File "C:\Users\User\AppData\Local\Programs\Python\Python313\Lib\site-packages\ChatTTS\model\tokenizer.py", line 19, in Tokenizer
    tokenizer_path: torch.serialization.FILE_LIKE,
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: module 'torch.serialization' has no attribute 'FILE_LIKE'

I googled the error message. But there was no matching results.

Priyaank · Accepted Answer · 2025-05-04 02:08:39Z

0

This is happening because you're using Python 3.13, which is not currently supported by PyTorch

You should downgrade to Python 3.10 or Python 3.9, which are stable with PyTorch and all its associated packages.

answered May 4 at 2:08

Priyaank

3101 silver badge9 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

Rhys May 4 at 16:23

thank you for responding. I will have to look into this.

Rhys May 12 at 8:04

I have put in a ticket here to follow the progress. github.com/2noise/ChatTTS/issues/933

Collectives™ on Stack Overflow

python 3.13 - ChatTTS transformer text to speech

1 Answer 1

2 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Related