miss hparams.yaml for inference
nukes opened this issue · comments
Martin Zheng commented
Hi, it seems that you did not upload the hparams.yaml for inference:
(py3.10) python inference.py inference \ [16:51:26]
--ckpt_path=model/dnr-bsrnn-gru8-vox7-l1-effects.ckpt \
--file_path=/soundx_speech_data/eval_audio/【走心短片】老师,你好!_01.wav \
--model_name=test_model
/data1/martinzheng/miniconda3/envs/py3.10/lib/python3.10/site-packages/torch_audiomentations/utils/io.py:27: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. With dispatcher enabled, this function is no-op. You can remove the function call.
torchaudio.set_audio_backend("soundfile")
Traceback (most recent call last):
File "/data1/martinzheng/tts/backend/bandit/inference.py", line 281, in <module>
fire.Fire()
File "/data1/martinzheng/miniconda3/envs/py3.10/lib/python3.10/site-packages/fire/core.py", line 141, in Fire
component_trace = _Fire(component, args, parsed_flag_args, context, name)
File "/data1/martinzheng/miniconda3/envs/py3.10/lib/python3.10/site-packages/fire/core.py", line 475, in _Fire
component, remaining_args = _CallAndUpdateTrace(
File "/data1/martinzheng/miniconda3/envs/py3.10/lib/python3.10/site-packages/fire/core.py", line 691, in _CallAndUpdateTrace
component = fn(*varargs, **kwargs)
File "/data1/martinzheng/tts/backend/bandit/inference.py", line 44, in inference
config: Dict = read_nested_yaml(os.path.join(ckpt_dir, "hparams.yaml"))
File "/data1/martinzheng/tts/backend/bandit/utils/config.py", line 47, in read_nested_yaml
config = read_yaml(path)
File "/data1/martinzheng/tts/backend/bandit/utils/config.py", line 12, in read_yaml
with open(path, "r") as f:
FileNotFoundError: [Errno 2] No such file or directory: 'hparams.yaml'
Karn Watcharasupat commented
Please get the relevant config file from the expt
folder and place them in the same folder as the checkpoint.