sample audio infer error _lzma.LZMAError: Corrupt input data

[cncbec]

My code :

from tools.audio import load_audio

from tools.normalizer import normalizer_en_nemo_text, normalizer_zh_tn

import ChatTTS
import scipy
import numpy as np
import torch
from typing import Optional

chat = ChatTTS.Chat()
is_load = chat.load(source='local')

# Define the function
def on_upload_sample(sample_audio_input: Optional[str]) -> str:
    if sample_audio_input is None:
        return ""
    sample_audio = torch.tensor(load_audio(sample_audio_input, 24000)).to('cuda')
    spk_smp = chat.sample_audio_speaker(sample_audio)
    del sample_audio
    return spk_smp
    
spk = on_upload_sample(r"./origin.WAV")
# spk = torch.load('青年女生.pth')

reftext = chat.infer("嗨怪怪星，这是我刚配的隐形眼镜，终于可以摆脱沉重的眼镜，以后，以后再也不会有人。", refine_text_only=True)
print(reftext[0])
params_infer_code = ChatTTS.Chat.InferCodeParams(
    spk_emb=spk,  # add sampled speaker
    txt_smp=reftext[0],
    temperature = .3,      # using custom temperature
    top_P = 0.7,           # top P decode
    top_K = 20,            # top K decode
)

params_refine_text = ChatTTS.Chat.RefineTextParams(
    prompt='[oral_1][laugh_2][break_6]',
)

tmp_text = "频泛化功能是指数字人能够自动适应多种视频内容，从中提取20元的关键信息并进行处理的能力" #阿拉伯数字中文化
wavs = chat.infer(tmp_text, params_refine_text=params_refine_text, params_infer_code=params_infer_code, use_decoder=True)
scipy.io.wavfile.write(filename=f"./4.wav", rate=24000, data=wavs[0].T)

but out:

嗨 [uv_break] 怪 怪 星 [uv_break] ， 这 是 我 刚 配 的 隐 形 眼 镜 [uv_break] ， 终 于 可 以 摆 脱 沉 重 的 眼 镜 [uv_break] ， 以 后 ， 以  
后 再 也 不 会 有 人 [uv_break] 。
found invalid characters: {'2', '0'}
text:  12%|████████████▏                                                                                    | 48/384(max) [00:01, 44.37it/s]
Traceback (most recent call last):
  File "D:\python_project\chattts\ChatTTS\clone.py", line 50, in <module>
    wavs = chat.infer(tmp_text, params_refine_text=params_refine_text, params_infer_code=params_infer_code, use_decoder=True)
  File "D:\python_project\chattts\ChatTTS\ChatTTS\core.py", line 220, in infer
    return next(res_gen)
  File "D:\python_project\chattts\ChatTTS\ChatTTS\core.py", line 390, in _infer
    for result in self._infer_code(
  File "F:\anaconda\envs\chattts\lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "D:\python_project\chattts\ChatTTS\ChatTTS\core.py", line 551, in _infer_code
    self.speaker.apply(
  File "F:\anaconda\envs\chattts\lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "D:\python_project\chattts\ChatTTS\ChatTTS\model\speaker.py", line 32, in apply
    spk_emb_tensor = torch.from_numpy(self._decode(spk_emb))
  File "D:\python_project\chattts\ChatTTS\ChatTTS\model\speaker.py", line 148, in _decode
    lzma.decompress(
  File "F:\anaconda\envs\chattts\lib\lzma.py", line 342, in decompress
    res = decomp.decompress(data)
_lzma.LZMAError: Corrupt input data

[fumiama]

传参有误，不要传给spk_emb。

[cncbec]

Thank you.

[github-actions]

This issue was closed because it has been inactive for 15 days since being marked as stale.