Open vcoopers opened 6 hours ago
Looks like the model files are missing, if you cloned the repo, you can find the model files in the zip file in releases. Replace the plugins/gptsovits folder with the one from the zip file.
Thanks, it works! I redid the installation using your method instead of grabbing it from Git. Everything's good now. You're a genius! I'm really enjoying your AIVTuber program.
Is there a way you can show me how to display English subtitles if the AI YouTuber is speaking in Japanese?
Hi, wondering if you can help...I.m facing an issue when loading the main.py
Traceback (most recent call last): File "C:\CP\LocalAIVtuber\venv\lib\site-packages\transformers\utils\hub.py", line 403, in cached_file resolved_file = hf_hub_download( File "C:\CP\LocalAIVtuber\venv\lib\site-packages\huggingface_hub\utils_deprecation.py", line 101, in inner_f return f(*args, **kwargs) File "C:\CP\LocalAIVtuber\venv\lib\site-packages\huggingface_hub\utils_validators.py", line 106, in _inner_fn validate_repo_id(arg_value) File "C:\CP\LocalAIVtuber\venv\lib\site-packages\huggingface_hub\utils_validators.py", line 154, in validate_repo_id raise HFValidationError( huggingface_hub.errors.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': 'C:\CP\LocalAIVtuber\plugins\gpt_sovits\GPT_SoVITS./pretrained_models/chinese-roberta-wwm-ext-large'. Use
repo_type
argument if needed.The above exception was the direct cause of the following exception:
Traceback (most recent call last): File "C:\CP\LocalAIVtuber\main.py", line 30, in
tts = TTS()
File "C:\CP\LocalAIVtuber\TTS.py", line 39, in init
super().init(TTSPluginInterface)
File "C:\CP\LocalAIVtuber\pluginSelectionBase.py", line 36, in init
self.load_provider(provider.name)
File "C:\CP\LocalAIVtuber\pluginSelectionBase.py", line 67, in load_provider
found_provider.plugin.init()
File "C:\CP\LocalAIVtuber\plugins\gpt_sovits\gptSovits.py", line 50, in init
self.load_voice_config()
File "C:\CP\LocalAIVtuber\plugins\gpt_sovits\gptSovits.py", line 47, in load_voice_config
api.init(sovits_path, gpt_path, reference_audio_path, reference_audio_text, reference_audio_language)
File "C:\CP\LocalAIVtuber\plugins\gpt_sovits\GPT_SoVITS\api_direct.py", line 142, in init
tokenizer = AutoTokenizer.from_pretrained(bert_path)
File "C:\CP\LocalAIVtuber\venv\lib\site-packages\transformers\models\auto\tokenization_auto.py", line 844, in from_pretrained
tokenizer_config = get_tokenizer_config(pretrained_model_name_or_path, **kwargs)
File "C:\CP\LocalAIVtuber\venv\lib\site-packages\transformers\models\auto\tokenization_auto.py", line 676, in get_tokenizer_config
resolved_config_file = cached_file(
File "C:\CP\LocalAIVtuber\venv\lib\site-packages\transformers\utils\hub.py", line 469, in cached_file
raise EnvironmentError(
OSError: Incorrect path_or_model_id: 'C:\CP\LocalAIVtuber\plugins\gpt_sovits\GPT_SoVITS./pretrained_models/chinese-roberta-wwm-ext-large'. Please provide either the path to a local folder or the repo_id of a model on the Hub.