douglas125 / SpeechCmdRecognition

A neural attention model for speech command recognition
MIT License
180 stars 78 forks source link

issues with ConvSpeechModel tensorflow version #10

Closed prasanna10 closed 2 years ago

prasanna10 commented 3 years ago

what is the exact tensorflow version used which will solve this error of dense input shape Im using this 2.0.0 but still no solution

Anurag-Varma commented 2 years ago

AssertionError: Hey! The input is too short!

getting the above error in the line:-

model = SpeechModels.AttRNNSpeechModel(nCategories=nCategs, samplingrate = sr, inputLength = None)#, rnn_func=L.LSTM)

UPDATE: solved it by using tensorflow 2.7.0, previously used 1.15.0 and got the above error

douglas125 commented 2 years ago

Thanks for that. Closing. (For some reason I sometimes don't get github msgs on issues)