Can you make audio-classification by YAMNet model?

[zxl777]

download the YAMNet model from https://tfhub.dev/google/lite-model/yamnet/classification/tflite/1

[Caldarie]

Looking at the input (float32[15600]) and output (float32[1,521]), it looks like you can load it with rawAudio.

If it doesn't work, you can modify the code to fit the input and output. To find these values, load your model here and adjust the values on this packages accordingly.

[zxl777]

Can you take a look at the introduction of yamnet, which was originally the most authoritative audio classification model of Google.

https://tfhub.dev/google/yamnet/1

https://www.tensorflow.org/lite/examples/audio_classification/overview

[Caldarie]

Can you take a look at the introduction of yamnet, which was originally the most authoritative audio classification model of Google.

https://tfhub.dev/google/yamnet/1

https://www.tensorflow.org/lite/examples/audio_classification/overview

I’m sorry, I’m not sure that I follow your request.

Are you asking whether this model is adaptable to this plugin?