[Bug] bug in tts_to_file

[forthcoming]

Describe the bug

from TTS.api import TTS

tts_ins = TTS('tts_models/multilingual/multi-dataset/xtts_v2')
tts_ins.tts_to_file(
    text='因为树脂这个材料它比较容易染色所以久了之后呢树脂贴片就没有刚开始那么漂亮了那再来就是树脂这个材料它比较软。',
    file_path="output.wav",
    speaker="Ana Florence",  # 使用默认的人声
    language="zh-cn",
    split_sentences=True,
)

when I run this code,the output.wav will most likely repeat the last few words of the text.How is this going? thanks

To Reproduce

from TTS.api import TTS

tts_ins = TTS('tts_models/multilingual/multi-dataset/xtts_v2')
tts_ins.tts_to_file(
text='因为树脂这个材料它比较容易染色所以久了之后呢树脂贴片就没有刚开始那么漂亮了那再来就是树脂这个材料它比较软。',
file_path="output.wav",
speaker="Ana Florence", # 使用默认的人声
language="zh-cn",
split_sentences=True,
)

Expected behavior

No response

Logs

No response

Environment

{
    "CUDA": {
        "GPU": [],
        "available": false,
        "version": null
    },
    "Packages": {
        "PyTorch_debug": false,
        "PyTorch_version": "2.2.1",
        "TTS": "0.22.0",
        "numpy": "1.26.4"
    },
    "System": {
        "OS": "Darwin",
        "architecture": [
            "64bit",
            ""
        ],
        "processor": "arm",
        "python": "3.11.5",
        "version": "Darwin Kernel Version 23.3.0: Wed Dec 20 21:33:31 PST 2023; root:xnu-10002.81.5~7/RELEASE_ARM64_T8112"
    }
}

Additional context

none

[stale]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. You might also look our discussion channels.