conformer
conformer copied to clipboard
[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)
Is there any possibility to use pre-trained conformer model for feature extraction on another speech dataset. Have you uploaded your pre-trained model and is there any tutorial how to extract...
Hello. I am currently using this package. I'm afraid this may be a basic question, but I'd like to ask a question. 1 Is the input a spectrogram or raw...
For mutihead-attention, I confused that no mask is passed in. Will it work ?
sir,can you explain the real usage of the example code ,I can't understand. please connect it with ASR or CV,thanks.
The output of DecoderRNN-T is combined with 4 dimensions, how to use it to recognize speech? Besides, the auther make the model architecture with the LAS? Such as: Conformer-Encoder, LSTM-Decoder,...
I have installed the package and after run the usage sample. there comes an error like following: RuntimeError: Gather got an input of invalid size: got [1, 3085, 8, 10],...
There's one thing I don't understand。Why do have to change the one-quarter sampling rate? How does it help? Thanks.
Hi, I am a little confused, if I want to export the onnx, should I use the forward or the recognize function? The difference seems to be that in the...
Hi, There is a problem about training a conformer+RNN-T model. How about the cer and wer with one GPU? I'm train the model on one RTX TITAN GPU, training the...