issues installing and running gradio on windows

[chille9]

Hi! Im trying to run the cli gradio interface but getting a weird error. I tried solving it to no avail.

Ive double checked the moss_tts_app.py has a backslash in the code.

(moss-tts) C:\AI\MOSS-TTS>python clis/moss_tts_app.py
[INFO] Using attn_implementation=sdpa
[Startup] Preloading backend: model=OpenMOSS-Team/MOSS-TTS, device=cuda:0, attn=sdpa
Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.
chat_template.jinja: 100%|██████████████████████████████████████████████████████████████████████████████████| 352/352 [00:00<?, ?B/s]
A new version of the following files was downloaded from https://huggingface.co/OpenMOSS-Team/MOSS-TTS:

• configuration_moss_tts.py
  . Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.
  Traceback (most recent call last):
  File "C:\Users\Jabulsh\anaconda3\envs\moss-tts\Lib\site-packages\transformers\utils\hub.py", line 419, in cached_files
  hf_hub_download(
  File "C:\Users\Jabulsh\anaconda3\envs\moss-tts\Lib\site-packages\huggingface_hub\utils_validators.py", line 85, in inner_fn
  validate_repo_id(arg_value)
  File "C:\Users\Jabulsh\anaconda3\envs\moss-tts\Lib\site-packages\huggingface_hub\utils_validators.py", line 135, in validate_repo_id
  raise HFValidationError(
  huggingface_hub.errors.HFValidationError: Repo id must use alphanumeric chars, '-', '' or '.'. The name cannot start or end with '-' or '.' and the maximum length is 96: 'OpenMOSS-Team\MOSS-TTS'.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "C:\AI\MOSS-TTS\clis\moss_tts_app.py", line 621, in
main()
File "C:\AI\MOSS-TTS\clis\moss_tts_app.py", line 602, in main
load_backend(
File "C:\AI\MOSS-TTS\clis\moss_tts_app.py", line 90, in load_backend
processor = AutoProcessor.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Jabulsh\anaconda3\envs\moss-tts\Lib\site-packages\transformers\models\auto\processing_auto.py", line 392, in from_pretrained
return processor_class.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Jabulsh.cache\huggingface\modules\transformers_modules\OpenMOSS_hyphen_Team\MOSS_hyphen_TTS\0c8df9988ab61071cdb06fe40b2bdc3132ac3b7e\processing_moss_tts.py", line 205, in from_pretrained
AutoConfig.from_pretrained(
File "C:\Users\Jabulsh\anaconda3\envs\moss-tts\Lib\site-packages\transformers\models\auto\configuration_auto.py", line 1356, in from_pretrained
config_dict, unused_kwargs = PreTrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Jabulsh\anaconda3\envs\moss-tts\Lib\site-packages\transformers\configuration_utils.py", line 569, in get_config_dict
config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Jabulsh\anaconda3\envs\moss-tts\Lib\site-packages\transformers\configuration_utils.py", line 624, in get_config_dict
resolved_config_file = cached_file(
^^^^^^^^^^^^
File "C:\Users\Jabulsh\anaconda3\envs\moss-tts\Lib\site-packages\transformers\utils\hub.py", line 276, in cached_file
file = cached_files(path_or_repo_id=path_or_repo_id, filenames=[filename], **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Jabulsh\anaconda3\envs\moss-tts\Lib\site-packages\transformers\utils\hub.py", line 468, in cached_files
raise OSError(f"{e}") from e
OSError: Repo id must use alphanumeric chars, '-', '' or '.'. The name cannot start or end with '-' or '.' and the maximum length is 96: 'OpenMOSS-Team\MOSS-TTS'.

[Redtash1]

I had to created a folder in the root of MOSS-TTS called "ckpts" & git clone all the models into that folder. I created a custom app.py file that combines the 4 moss_tts_app.py files into a single app.py file along with some tweaks to speed up the generation times. It works right now but there are still many more things I want to tweak but I ran out of free Google Ai Studio time, so I have to wait until tonight to continue. I can share what I have working now if you'd like? Warning that MOSS-TTS uses over 16GB VRAM & 8GB Shared Memory & it's kind of slow.