qiuqiangkong / audioset_tagging_cnn

MIT License
1.32k stars 249 forks source link

Input wav's time length for model "Wavegram_Logmel_Cnn14"? #29

Open machengnan opened 3 years ago

machengnan commented 3 years ago

Is there a requirement for Input wav's time length? 4s or 2s or any time?

I think this line code "x = torch.cat((x, a1), dim=1)" decide time length should be a certain value,right?

qiuqiangkong commented 3 years ago

The Wavegram_Logmel_Cnn14 is fixed to 10-second audio now. It is suggested to use Cnn14 which also performs well, and is flexible to any duration of audio clip.