KevinKrames
commented
1 year ago Looks like I was finally able to solve my issue, Poetry was using the wrong version of python. For some reason I could not change the python version in poetry by defining setting the path to my local version (Was getting access denied even in admin cmd). Instead I had to install pyenv here: https://github.com/pyenv-win/pyenv-win Then I had to change the python env using pyenv: pyenv install 3.9.11 poetry env use $(pyenv which python)
Hey guys I'm trying to run the code on my machine and I'm having trouble loading the checkpoint using torch: warn(f"Failed to load image Python extension: {e}") ╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮ │ X:\tortoise-tts-faster2\scripts\tortoise_tts.py:223 in │
│ │
│ 220 │ # app = import_module("app") │
│ 221 │ # sys.exit(app.main()) │
│ 222 │ │
│ ❱ 223 │ from tortoise.inference import ( │
│ 224 │ │ check_pydub, │
│ 225 │ │ get_all_voices, │
│ 226 │ │ get_seed, │
│ │
│ X:\tortoise-tts-faster2\tortoise\inference.py:167 in │
│ │
│ 164 │
│ 165 from voicefixer import VoiceFixer │
│ 166 │
│ ❱ 167 vfixer = VoiceFixer() │
│ 168 │
│ 169 │
│ 170 def save_gen_with_voicefix(g, fpath, squeeze=True, voicefixer=True): │
│ │
│ C:\Users*\AppData\Local\Programs\Python\Python310\lib\site-packages\voicefixer\base. │
│ py:13 in init │
│ │
│ 10 class VoiceFixer(nn.Module): │
│ 11 │ def init(self): │
│ 12 │ │ super(VoiceFixer, self).init() │
│ ❱ 13 │ │ self._model = voicefixer_fe(channels=2, sample_rate=44100) │
│ 14 │ │ # print(os.path.join(os.path.expanduser('~'), ".cache/voicefixer/analysis_module │
│ 15 │ │ self.analysis_module_ckpt = os.path.join( │
│ 16 │ │ │ │ │ os.path.expanduser("~"), │
│ │
│ C:\Users*r\AppData\Local\Programs\Python\Python310\lib\site-packages\voicefixer\resto │
│ rer\model.py:180 in init │
│ │
│ 177 │ │ # self.am = AudioMetrics() │
│ 178 │ │ # self.im = ImgMetrics() │
│ 179 │ │ │
│ ❱ 180 │ │ self.vocoder = Vocoder(sample_rate=44100) │
│ 181 │ │ │
│ 182 │ │ self.valid = None │
│ 183 │ │ self.fake = None │
│ │
│ C:\Users*\AppData\Local\Programs\Python\Python310\lib\site-packages\voicefixer\vocod │
│ er\base.py:19 in init │
│ │
│ 16 │ │ │ raise RuntimeError("Error 1: The checkpoint for synthesis module / vocoder ( │
│ 17 │ │ │ │ │ │ │ │ By default the checkpoint should be download automatical │
│ 18 │ │ │ │ │ │ │ │ But don't worry! Alternatively you can download it direc │
│ ❱ 19 │ │ self._load_pretrain(Config.ckpt) │
│ 20 │ │ self.weight_torch = Config.get_mel_weight_torch(percent=1.0)[ │
│ 21 │ │ │ None, None, None, ... │
│ 22 │ │ ] │
│ │
│ C:\Users*\AppData\Local\Programs\Python\Python310\lib\site-packages\voicefixer\vocod │
│ er\base.py:26 in _load_pretrain │
│ │
│ 23 │ │
│ 24 │ def _load_pretrain(self, pth): │
│ 25 │ │ self.model = Generator(Config.cin_channels) │
│ ❱ 26 │ │ checkpoint = load_checkpoint(pth, torch.device("cpu")) │
│ 27 │ │ load_try(checkpoint["generator"], self.model) │
│ 28 │ │ self.model.eval() │
│ 29 │ │ self.model.remove_weight_norm() │
│ │
│ C:\Users*\AppData\Local\Programs\Python\Python310\lib\site-packages\voicefixer\vocod │
│ er\model\util.py:111 in load_checkpoint │
│ │
│ 108 │
│ 109 │
│ 110 def load_checkpoint(checkpoint_path, device): │
│ ❱ 111 │ checkpoint = torch.load(checkpoint_path, map_location=device) │
│ 112 │ return checkpoint │
│ 113 │
│ 114 │
│ │
│ C:\Users*\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serializat │
│ ion.py:777 in load │
│ │
│ 774 │ │ │ # If we want to actually tail call to torch.jit.load, we need to │
│ 775 │ │ │ # reset back to the original position. │
│ 776 │ │ │ orig_position = opened_file.tell() │
│ ❱ 777 │ │ │ with _open_zipfile_reader(opened_file) as opened_zipfile: │
│ 778 │ │ │ │ if _is_torchscript_zip(opened_zipfile): │
│ 779 │ │ │ │ │ warnings.warn("'torch.load' received a zip file that looks like a To │
│ 780 │ │ │ │ │ │ │ │ " dispatching to 'torch.jit.load' (call 'torch.jit.loa │
│ │
│ C:\Users***\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serializat │
│ ion.py:282 in init │
│ │
│ 279 │
│ 280 class _open_zipfile_reader(_opener): │
│ 281 │ def init(self, name_or_buffer) -> None: │
│ ❱ 282 │ │ super(_open_zipfile_reader, self).init(torch._C.PyTorchFileReader(name_or_bu │
│ 283 │
│ 284 │
│ 285 class _open_zipfile_writer_file(_opener): │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory
I thought maybe the file was imcomplete and tried to delete it and dowload it manually through the browser but I'm still having the same issue. Thanks for any help!