[Bug] Voice lag and pronounce punctuation

[Razatator]

Describe the bug

When I create a model to imitate a voice for dubbing it comes out with stutters as if the character had Down syndrome sometimes and it pronounces 'point' at the end of sentences in French. On other imitations, there were Japanese voices in the background. Since installing the V2 model
I went back to version 0.21 and 0.22 as explained but still the bugs.

To Reproduce

https://colab.research.google.com/github/R3gm/SoniTranslate/blob/main/SoniTranslate_Colab.ipynb

Expected behavior

No response

Logs

anaconda3/TTS/bin/collect_env_info.py dont work

Environment

{
    "CUDA": {
        "GPU": [
            "NVIDIA GeForce GTX 1060 with Max-Q Design"
        ],
        "available": true,
        "version": "12.1"
    },
    "Packages": {
        "PyTorch_debug": false,
        "PyTorch_version": "2.2.2",
        "TTS": "0.22.0",
        "numpy": "1.26.4"
    },
    "System": {
        "OS": "Linux",
        "architecture": [
            "64bit",
            "ELF"
        ],
        "processor": "x86_64",
        "python": "3.10.14",
        "version": "#13-Ubuntu SMP PREEMPT_DYNAMIC Fri Feb 16 00:01:45 UTC 2024"
    }
}

Additional context

I use TTS in this environment https://github.com/R3gm/SoniTranslate in anaconda3