很奇怪的问题

[SMK1311]

这是我的代码
``import os
import torch
import torchaudio
from TTS.tts.configs.xtts_config import XttsConfig
from TTS.tts.models.xtts import Xtts

print("Loading model...")
config = XttsConfig()
config.load_json("/aia-storage/root/liyingjun/TTS/run/training/GPT_XTTS_v2.0_LJSpeech_FT-May-21-2025_06+00PM-dbf1a08a/config.json")
model = Xtts.init_from_config(config)
model.load_checkpoint(config, checkpoint_dir='/aia-storage/root/liyingjun/TTS/run/training/XTTS_v2.0_original_model_files', use_deepspeed=True, vocab_path='/aia-storage/root/liyingjun/TTS/run/training/XTTS_v2.0_original_model_files/vocab.json')
model.cuda()

print("Computing speaker latents...")
gpt_cond_latent, speaker_embedding = model.get_conditioning_latents(audio_path=["/aia-storage/root/liyingjun/TTS/mix-yinpin/zh-data/wavs/EN_1238_ZH_SZH115.wav"])

print("Inference...")
out = model.inference(
"当然，如果您需要的话，这边帮您准备。",
"zh",
gpt_cond_latent,
speaker_embedding,
temperature=0.7, # Add custom parameters here
)
torchaudio.save("xtts.wav", torch.tensor(out["wav"]).unsqueeze(0), 24000)``
这是我的路径

我很奇怪为什么我的checkpoint_dir不是GPT_XTTS_v2.0_LJSpeech_FT-May-21-2025_06+00PM-dbf1a08a而是要在XTTS_v2.0_original_model_files下 我这样操作是对的吗？