dawidkopczyk / speech_recognition Goto Github PK

View Code? Open in Web Editor NEW

8.0 8.0 5.0 5 KB

Python 100.00%

speech_recognition's People

Contributors

Stargazers

Watchers

Forkers

techgopal ahmadiphy thoqus adanlbenito loverui0

speech_recognition's Issues

can't able to train the model

ValueError: validation_steps=None is only valid for a generator based on the keras.utils.Sequence class. Please specify validation_steps or use the keras.utils.Sequence class.

and the value of "int(np.ceil(len(dsGen.df_val)/BATCH))" and "int(np.ceil(len(dsGen.df_train)/BATCH))" is 0.

The model doesn't save checkpoints

In main.py there isn't any code that permit to save checkpoints or export model. I try to add model.save('trained.h5') after history = ... but it doesn't work. Anyone knows how to resolve this problem?
I need to obtain h5 trained model.

list index out of range

I can't understand why this error occurred!?

Traceback (most recent call last):
File "main.py", line 24, in
df = dsGen.load_data(DIR)
File "./dataset.py", line 40, in load_data
wav_files = [x.split(sep='\')[1] + '/' + x.split(sep='\')[2] for x in wav_files]
File "./dataset.py", line 40, in
wav_files = [x.split(sep='\')[1] + '/' + x.split(sep='\')[2] for x in wav_files]
IndexError: list index out of range

Recommend Projects