augmented tinyset analysis: mixed frequency issue
fingerprinting with frequency 11500 (this will change to 12000 after using pydub)
inference with frequency 12000 (which is produced by loading and save 11500 audios with torchaudio)
- 4-sec window
- no splitting
Created on May 16|Last edited on May 20
Comment
Section 1
Run set
373
Add a comment