Synthesize--ValueError: could not convert string to float: 'training_data/mels\\speech-mel-00001.npy'

[Rita-ritally]

when i ran python synthesize.py --model ='Tacotron'--mode ='eval'--reference_audio ='ref_1.wav' ,an issue occured!
ValueError: could not convert string to float: 'training_data/mels\speech-mel-00001.npy'

please help me solving this problem
thanks!!!

[Rita-ritally]

Loading checkpoint: logs-Tacotron/pretrained/model.ckpt-9500
Loaded metadata for 13100 examples (23.94 hours)
starting synthesis
0%| | 0/13100 [00:00<?, ?it/s]
Traceback (most recent call last):
File "synthesize.py", line 34, in
main()
File "synthesize.py", line 28, in main
tacotron_synthesize(args)
File "E:\cuc\2020\code\vae_tacotron2\tacotron\synthesize.py", line 79, in tacotron_synthesize
run_synthesis(args, checkpoint_path, output_dir)
File "E:\cuc\2020\code\vae_tacotron2\tacotron\synthesize.py", line 60, in run_synthesis
mel_output_filename = synth.synthesize(text, None, i+1, synth_dir, None, mel_filename)
File "E:\cuc\2020\code\vae_tacotron2\tacotron\synthesizer.py", line 58, in synthesize
reference_mel = [np.asarray(reference_mel, dtype=np.float32)]
File "D:\Anaconda3\envs\tf1.6\lib\site-packages\numpy\core\numeric.py", line 531, in asarray
return array(a, dtype, copy=False, order=order)
ValueError: could not convert string to float: 'training_data/mels\speech-mel-00001.npy'