Cannot retrieve the public link of the file when running espnet_tts_demo

[Huan-phonetic]

Describe your question

Dear developers,

I'm trying the espnet_tts_demo script in colab. But got trouble in these lines:

from espnet2.bin.tts_inference import Text2Speech
from espnet2.utils.types import str_or_none
text2speech = Text2Speech.from_pretrained(
model_tag=str_or_none(tag),
vocoder_tag=str_or_none(vocoder_tag),
device="cuda",
# Only for Tacotron 2 & Transformer
threshold=0.5,
# Only for Tacotron 2
minlenratio=0.0,
maxlenratio=10.0,
use_att_constraint=False,
backward_window=1,
forward_window=3,
# Only for FastSpeech & FastSpeech2 & VITS
speed_control_alpha=1.0,
# Only for VITS
noise_scale=0.333,
noise_scale_dur=0.333,
)

For some pre-trained models, this assignment works fine and the synthesis is good. But for some other models like:

lang = 'English'
tag = 'kan-bayashi/ljspeech_fastspeech2'
vocoder_tag = "parallel_wavegan/ljspeech_hifigan.v1"

It shows below errors.

https://zenodo.org/record/4036272/files/tts_train_fastspeech2_raw_phn_tacotron_g2p_en_no_space_train.loss.ave.zip?download=1: 100%|██████████| 142M/142M [02:22<00:00, 1.05MB/s]
/usr/local/lib/python3.10/dist-packages/espnet_model_zoo/downloader.py:364: UserWarning: Not validating checksum
warnings.warn("Not validating checksum")
Access denied with the following error:

Cannot retrieve the public link of the file. You may need to change
the permission to 'Anyone with the link', or have had many accesses. 

You may still be able to access the file from the browser:
https://drive.google.com/uc?id=1i6-hR_ksEssCYNlNII86v3AoeA1JcuWD

FileNotFoundError Traceback (most recent call last)
in <cell line: 4>()
2 from espnet2.utils.types import str_or_none
3
----> 4 text2speech = Text2Speech.from_pretrained(
5 model_tag=str_or_none(tag),
6 vocoder_tag=str_or_none(vocoder_tag),
4 frames
/usr/lib/python3.10/gzip.py in init(self, filename, mode, compresslevel, fileobj, mtime)
172 mode += 'b'
173 if fileobj is None:
--> 174 fileobj = self.myfileobj = builtins.open(filename, mode or 'rb')
175 if filename is None:
176 filename = getattr(fileobj, 'name', '')
FileNotFoundError: [Errno 2] No such file or directory: '/root/.cache/parallel_wavegan/ljspeech_hifigan.v1.tar.gz'

Though I can manually download the model file .tar.gz from google drive, I don't know how to load it into this script. I checked the issue histories and found some simliar problems with access deny. Guess it's still something to do with Google Drive permission.

Would you please share the permission or invite me to the email list?