在ubuntu系统训练时，找不到train.txt目录

如图。在windows端完全没问题，但上服务器就报错
(base) root@f7a701305fdd:~/data/MockingBird-main# python synthesizer_train.py 22 data/datasets_root/SV2TTS/synthesizer
Arguments:
run_id: 22
syn_dir: data/datasets_root/SV2TTS/synthesizer
models_dir: synthesizer/saved_models/
save_every: 1000
backup_every: 25000
log_every: 200
force_restart: False
hparams:

Checkpoint path: synthesizer/saved_models/22/22.pt
Loading training data from: data/datasets_root/SV2TTS/synthesizer/train.txt
Using model: Tacotron
Using device: cuda

Initialising Tacotron Model...

Trainable Parameters: 32.869M

Loading weights at synthesizer/saved_models/22/22.pt
Tacotron weights loaded from step 0
Using inputs from:
data/datasets_root/SV2TTS/synthesizer/train.txt
data/datasets_root/SV2TTS/synthesizer/mels
data/datasets_root/SV2TTS/synthesizer/embeds
Traceback (most recent call last):
File "synthesizer_train.py", line 37, in
train(**vars(args))
File "/root/data/MockingBird-main/synthesizer/train.py", line 121, in train
dataset = SynthesizerDataset(metadata_fpath, mel_dir, embed_dir, hparams)
File "/root/data/MockingBird-main/synthesizer/synthesizer_dataset.py", line 12, in __init__
with metadata_fpath.open("r", encoding="utf-8") as metadata_file:
File "/root/miniconda3/lib/python3.8/pathlib.py", line 1218, in open
return io.open(self, mode, buffering, encoding, errors, newline,
File "/root/miniconda3/lib/python3.8/pathlib.py", line 1074, in _opener
return self._accessor.open(self, flags, mode)
FileNotFoundError: [Errno 2] No such file or directory: 'data/datasets_root/SV2TTS/synthesizer/train.txt'
`

Start with the command in synthesizer_train.py and trace the reported path through synthesizer/train.py into synthesizer/synthesizer_dataset.py. Reproduce the Ubuntu training command and inspect how data/datasets_root/SV2TTS/synthesizer/train.txt is expected to be provided. Done means the dataset path is resolved and training proceeds past metadata loading.

Written by the indexing model from the issue text.