AI4Bharat / IndicWav2Vec

Pretraining, fine-tuning and evaluation scripts for Indic-Wav2Vec2
https://indicnlp.ai4bharat.org/indicwav2vec
MIT License
82 stars 28 forks source link

Model file not found #17

Closed shihabtechno closed 2 years ago

shihabtechno commented 2 years ago

While running "python app/flask_api.py" this command, I get this error how can I get rid of this error?

return self._float_to_str(self.smallest_subnormal) Traceback (most recent call last): File "/home/shihab/Projects/indicwav2back/IndicWav2Vec/ULCA_Compliance/app/support.py", line 238, in load_model mdl, cfg, task = fairseq.checkpoint_utils.load_model_ensemble_and_task([mdl_path]) File "/home/shihab/Projects/indicwav2back/IndicWav2Vec/venv/lib/python3.8/site-packages/fairseq/checkpoint_utils.py", line 278, in load_model_ensemble_and_task raise IOError("Model file not found: {}".format(filename)) OSError: Model file not found: /new_disk/models/bn/bn.pt

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "app/flask_api.py", line 28, in model, dictionary = load_model(m['model_path']) File "/home/shihab/Projects/indicwav2back/IndicWav2Vec/ULCA_Compliance/app/support.py", line 243, in load_model m = torch.load(mdl_path) File "/home/shihab/Projects/indicwav2back/IndicWav2Vec/venv/lib/python3.8/site-packages/torch/serialization.py", line 594, in load with _open_file_like(f, 'rb') as opened_file: File "/home/shihab/Projects/indicwav2back/IndicWav2Vec/venv/lib/python3.8/site-packages/torch/serialization.py", line 230, in _open_file_like return _open_file(name_or_buffer, mode) File "/home/shihab/Projects/indicwav2back/IndicWav2Vec/venv/lib/python3.8/site-packages/torch/serialization.py", line 211, in init super(_open_file, self).init(open(name, mode)) FileNotFoundError: [Errno 2] No such file or directory: '/new_disk/models/bn/bn.pt'

tahirjmakhdoomi commented 2 years ago

Hi [shihabtechno]

There should be a json file containing paths to your model checkpoints. You will need to update your model paths there.